@article {pmid40051554,
year = {2025},
author = {Teman, SJ and Atwood, TC and Converse, SJ and Fry, TL and Laidre, KL},
title = {Measuring polar bear health using allostatic load.},
journal = {Conservation physiology},
volume = {13},
number = {1},
pages = {coaf013},
pmid = {40051554},
issn = {2051-1434},
abstract = {The southern Beaufort Sea polar bear sub-population (Ursus maritimus) has been adversely affected by climate change and loss of sea ice habitat. Even though the sub-population is likely decreasing, it remains difficult to link individual polar bear health and physiological change to sub-population effects. We developed an index of allostatic load, which represents potential physiological dysregulation. The allostatic load index included blood- and hair-based analytes measured in physically captured southern Beaufort bears in spring. We examined allostatic load in relation to bear body condition, age, terrestrial habitat use and, over time, for bear demographic groups. Overall, allostatic load had no relationship with body condition. However, allostatic load was higher in adult females without cubs that used terrestrial habitats the prior year, indicating potential physiological dysregulation with land use. Allostatic load declined with age in adult females without cubs. Sub-adult males demonstrated decreased allostatic load over time. Our study is one of the first attempts to develop a health scoring system for free-ranging polar bears, and our findings highlight the complexity of using allostatic load as an index of health in a wild species. Establishing links between individual bear health and population dynamics is important for advancing conservation efforts.},
}

@article {pmid40050621,
year = {2025},
author = {Cui, H and Xiao, Y and Yang, Y and Pei, M and Ke, S and Fang, X and Qiao, L and Shi, K and Long, H and Xu, W and Cai, P and Lin, P and Shi, Y and Wan, Q and Wan, C},
title = {A bioinspired in-materia analog photoelectronic reservoir computing for human action processing.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {2263},
pmid = {40050621},
issn = {2041-1723},
support = {92364106//National Natural Science Foundation of China (National Science Foundation of China)/ ; 92364204//National Natural Science Foundation of China (National Science Foundation of China)/ ; BK20220121//Natural Science Foundation of Jiangsu Province (Jiangsu Provincial Natural Science Foundation)/ ; },
mesh = {Humans ; *Algorithms ; Neural Networks, Computer ; Transistors, Electronic ; },
abstract = {Current computer vision is data-intensive and faces bottlenecks in shrinking computational costs. Incorporating physics into a bioinspired visual system is promising to offer unprecedented energy efficiency, while the mismatch between physical dynamics and bioinspired algorithms makes the processing of real-world samples rather challenging. Here, we report a bioinspired in-materia analogue photoelectronic reservoir computing for dynamic vision processing. Such system is built based on InGaZnO photoelectronic synaptic transistors as the reservoir and a TaOX-based memristor array as the output layer. A receptive field inspired encoding scheme is implemented, simplifying the feature extraction process. High recognition accuracies (>90%) on four motion recognition datasets are achieved based on such system. Furthermore, falling behaviors recognition is also verified by our system with low energy consumption for processing per action (~45.78 μJ) which outperforms most previous reports on human action processing. Our results are of profound potential for advancing computer vision based on neuromorphic electronics.},
}

Humans
*Algorithms
Neural Networks, Computer
Transistors, Electronic

@article {pmid40049535,
year = {2025},
author = {Kong, L and Zhang, Q and Wang, H and Xu, Y and Xu, C and Chen, Y and Lu, J and Hu, S},
title = {Exploration of the optimized portrait of omega-3 polyunsaturated fatty acids in treating depression: A meta-analysis of randomized-controlled trials.},
journal = {Journal of affective disorders},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jad.2025.03.006},
pmid = {40049535},
issn = {1573-2517},
abstract = {BACKGROUND: According to previous studies, omega-3 polyunsaturated fatty acids (PUFAs) are controversial for the efficacy of treating depression.

AIMS: This meta-analysis aims to investigate whether omega-3 PUFAs are able to treat depression, and find out the most beneficial clinical portrait.

METHODS: More than two reviewers searched six registries, and 36 studies were eventually considered eligible. The PRISMA guidelines were used for data extraction, Cochrane Handbook for quality assessment, and random effects model for data pooling.

OUTCOMES: Significant heterogeneity and publication bias were observed. According to the results, significant efficacy was detected in the overall analysis [SMD = -0.26, 95 % CI = (-0.41, -0.11)] and several subgroups, while total daily dosage might be a potential heterogeneity source (P < 0.05). No between-group difference was observed in the rate of response [RR = 0.99, 95 % CI = (0.82, 1.20)], remission [RR = 1.17, 95 % CI = (0.92, 1.48)], and adverse events [RR = 1.07, 95 % CI = (0.90, 1.29)]. Total daily intake of eicosapentaenoic acid (EPA) and remission rate conformed to linear correlation (P < 0.05).

CONCLUSIONS: 1) Omega-3 PUFAs might be effective in treating depression; 2) For Asian patients with mild to moderate depression and no other baseline medication, over 8 weeks of omega-3 PUFAs 1000-1500 mg/day with ratio of EPA/docosahexaenoic acid (DHA) between 1:1 and 2:1 might benefit the most; 3) Omega-3 PUFAs are no superior than placebo in rates of response, remission, and adverse events. Although several limitations exist, the evidence-based information provides guidance for clinical practice and directions for further research.

PROSPERO REGISTRATION NUMBER: CRD42023464823.},
}

@article {pmid39983236,
year = {2025},
author = {Phang, CR and Hirata, A},
title = {Explainable multiscale temporal convolutional neural network model for sleep stage detection based on electroencephalogram activities.},
journal = {Journal of neural engineering},
volume = {22},
number = {2},
pages = {},
doi = {10.1088/1741-2552/adb90c},
pmid = {39983236},
issn = {1741-2552},
mesh = {Humans ; *Electroencephalography/methods ; *Neural Networks, Computer ; *Sleep Stages/physiology ; Male ; Female ; Adult ; Polysomnography/methods ; Young Adult ; Middle Aged ; },
abstract = {Objective.Humans spend a significant portion of their lives in sleep (an essential driver of body metabolism). Moreover, as sleep deprivation could cause various health complications, it is crucial to develop an automatic sleep stage detection model to facilitate the tedious manual labeling process. Notably, recently proposed sleep staging algorithms lack model explainability and still require performance improvement.Approach.We implemented multiscale neurophysiology-mimicking kernels to capture sleep-related electroencephalogram (EEG) activities at varying frequencies and temporal lengths; the implemented model was named 'multiscale temporal convolutional neural network (MTCNN).' Further, we evaluated its performance using an open-source dataset (Sleep-EDF Database Expanded comprising 153 d of polysomnogram data).Main results.By investigating the learned kernel weights, we observed that MTCNN detected the EEG activities specific to each sleep stage, such as the frequencies, K-complexes, and sawtooth waves. Furthermore, regarding the characterization of these neurophysiologically significant features, MTCNN demonstrated an overall accuracy (OAcc) of 91.12% and a Cohen kappa coefficient of 0.86 in the cross-subject paradigm. Notably, it demonstrated an OAcc of 88.24% and a Cohen kappa coefficient of 0.80 in the leave-few-days-out analysis. Our MTCNN model also outperformed the existing deep learning models in sleep stage classification even when it was trained with only 16% of the total EEG data, achieving an OAcc of 85.62% and a Cohen kappa coefficient of 0.75 on the remaining 84% of testing data.Significance.The proposed MTCNN enables model explainability and it can be trained with lesser amount of data, which is beneficial to its application in the real-world because large amounts of training data are not often and readily available.},
}

Humans
*Electroencephalography/methods
*Neural Networks, Computer
*Sleep Stages/physiology
Male
Female
Adult
Polysomnography/methods
Young Adult
Middle Aged

@article {pmid40049458,
year = {2025},
author = {Premchand, B and Toe, KK and Wang, C and Wan, KR and Selvaratnam, T and Toh, VE and Ng, WH and Libedinsky, C and Chen, W and Lim, R and Cheng, MY and Gao, Y and Ang, KK and So, RQY},
title = {Comparing a BCI Communication System in a Patient with Multiple System Atrophy, with an animal model.},
journal = {Brain research bulletin},
volume = {},
number = {},
pages = {111289},
doi = {10.1016/j.brainresbull.2025.111289},
pmid = {40049458},
issn = {1873-2747},
abstract = {Paralysis affects many people worldwide, and the people affected often suffer from impaired communication. We developed a microelectrode-based Brain-Computer Interface (BCI) for enabling communication in patients affected by paralysis, and implanted it in a patient with Multiple System Atrophy (MSA), a neurodegenerative disease that causes widespread neural symptoms including paralysis. To verify the effectiveness of the BCI system, it was also tested by implanting it in a non-human primate (NHP). Data from the human and NHP were used to train binary classifiers two different types of machine learning models: a Linear Discriminant Analysis (LDA) model, and a Long Short-Term Memory (LSTM)-based Artificial Neural Network (ANN). The LDA model performed at up to 72.7% accuracy for binary decoding in the human patient, however, performance was highly variable and was much lower on most recording days. The BCI system was able to accurately decode movement vs non-movement in the NHP (accuracy using LDA: 82.7 ± 3.3%, LSTM: 83.7 ± 2.2%, 95% confidence intervals), however it was not able to with recordings from the human patient (accuracy using LDA: 47.0 ± 5.1%, LSTM: 44.6 ± 9.9%, 95% confidence intervals). We discuss how neurodegenerative diseases such as MSA can impede BCI-based communication, and postulate on the mechanisms by which this may occur.},
}

@article {pmid40049046,
year = {2025},
author = {Chai, C and Yang, X and Zheng, Y and Bin Heyat, MB and Li, Y and Yang, D and Chen, YH and Sawan, M},
title = {Multimodal fusion of magnetoencephalography and photoacoustic imaging based on optical pump: Trends for wearable and noninvasive Brain-Computer interface.},
journal = {Biosensors & bioelectronics},
volume = {278},
number = {},
pages = {117321},
doi = {10.1016/j.bios.2025.117321},
pmid = {40049046},
issn = {1873-4235},
abstract = {Wearable noninvasive brain-computer interface (BCI) technologies, such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), have experienced significant progress since their inception. However, these technologies have not achieved revolutionary advancements, largely because of their inherently low signal-to-noise ratio and limited penetration depth. In recent years, the application of quantum-theory-based optically pumped (OP) technologies, particularly optical pumped magnetometers (OPMs) for magnetoencephalography (MEG) and photoacoustic imaging (PAI) utilizing OP pulsed laser sources, has opened new avenues for development in noninvasive BCIs. These advanced technologies have garnered considerable attention owing to their high sensitivity in tracking neural activity and detecting blood oxygen saturation. This paper represents the first attempt to discuss and compare technologies grounded in OP theory by examining the technical advantages of OPM-MEG and PAI over traditional EEG and fNIRS. Furthermore, the paper investigates the theoretical and structural feasibility of hardware reuse in OPM-MEG and PAI applications.},
}

@article {pmid40048825,
year = {2025},
author = {Kacker, K and Chetty, N and Feldman, AK and Bennett, J and Yoo, PE and Fry, A and Lacomis, D and Harel, N and Nogueira, RG and Majidi, S and Opie, NL and Collinger, J and Oxley, T and Putrino, D and Weber, DJ},
title = {Motor activity in gamma and high gamma bands recorded with a Stentrode from the human motor cortex in two people with ALS.},
journal = {Journal of neural engineering},
volume = {},
number = {},
pages = {},
doi = {10.1088/1741-2552/adbd78},
pmid = {40048825},
issn = {1741-2552},
abstract = {This study examined the strength and stability of motor signals in low gamma and high gamma bands of vascular electrocorticograms (VECoG) recorded with endovascular stent-electrode arrays (Stentrodes) implanted in the superior sagittal sinus of two participants with severe paralysis due to Amyotrophic Lateral Sclerosis. Methods: VECoG signals were recorded from two participants in the COMMAND trial, an Early Feasibility Study of the Stentrode brain-computer interface (BCI) (NCT05035823). The participants performed attempted movements of their ankles or hands. The signals were band-pass filtered to isolate low gamma (30-70 Hz) and high gamma (70-200 Hz) components. The strength of VECoG motor activity was measured as signal-to-noise ratio (SNR) and the percentage change in signal amplitude between the rest and attempted movement epochs, which we termed depth of modulation (DoM). We trained and tested classifiers to evaluate the accuracy and stability of detecting motor intent. Results: Both low gamma and high gamma were modulated during attempted movements. For Participant 1, the average DoM across channels and sessions was 125.41 ± 17.53 % for low gamma and 54.23 ± 4.52 % for high gamma, with corresponding SNR values of 6.75 ± 0.37 dB and 3.69 ± 0.28 dB. For Participant 2, the average DoM was 22.77 ± 4.09 % for low gamma and 22.53 ± 2.04 % for high gamma, with corresponding SNR values of 1.72 ± 0.25 dB and 1.73 ± 0.13 dB. VECoG amplitudes remained significantly different between rest and move periods over the 3 - month testing period, with > 90 % accuracy in discriminating attempted movement from rest epochs for both participants. For Participant 1, the average DoM was strongest during attempted movements of both ankles, while for Participant 2, the DoM was greatest for attempted movement of the right hand. The overall classification accuracy was 91.43 % for Participant 1 and 70.37 % for Participant 2 in offline decoding of multiple attempted movements and rest conditions. Significance: By eliminating the need for open brain surgery, the Stentrode offers a promising BCI alternative, potentially enhancing access to BCIs for individuals with severe motor impairments. This study provides preliminary evidence that the Stentrode can detect discriminable signals indicating motor intent, with motor signal modulation observed over the 3 - month testing period reported here.},
}

@article {pmid40048822,
year = {2025},
author = {Berger, LM and Maia de Oliveira Wood, G and Kober, SE},
title = {Manipulating cybersickness in virtual reality-based neurofeedback and its effects on training performance.},
journal = {Journal of neural engineering},
volume = {},
number = {},
pages = {},
doi = {10.1088/1741-2552/adbd76},
pmid = {40048822},
issn = {1741-2552},
abstract = {Virtual Reality (VR) serves as a modern and powerful tool to enrich neurofeedback (NF) and brain-computer interface (BCI) applications as well as to achieve higher user motivation and adherence to training. However, between 20-80% of all the users develop symptoms of cybersickness (CS), such as nausea, oculomotor problems or disorientation during VR interaction, which influence user performance and behaviour in VR. Hence, we investigated whether CS-inducing VR paradigms influence the success of a NF training task. We tested 39 healthy participants (20 female) in a single-session VR-based NF study. One half of the participants was presented with a high CS-inducing VR-environment where movement speed, field of view and camera angle were varied in a CS-inducing fashion throughout the session and the other half underwent NF training in a less CS-inducing VR environment, where those parameters were held constant. The NF training consisted of 6 runs of 3 min each, in which participants should increase their sensorimotor rhythm (SMR, 12-15 Hz) while keeping artifact control frequencies constant (Theta 4-7 Hz, Beta 16-30 Hz). Heart rate and subjectively experienced CS were also assessed. The high CS-inducing condition tended to lead to more subjectively experienced CS nausea symptoms than the low CS-inducing condition. Further, women experienced more CS, a higher heart rate and showed a worse NF performance compared to men. However, the SMR activity during the NF training was comparable between both the high and low CS-inducing groups. Both groups were able to increase their SMR across feedback runs, although, there was a tendency of higher SMR power for male participants in the low CS group. Hence, sickness symptoms in VR do not necessarily impair NF/BCI training success. This takes us one step further in evaluating the practicability of VR in BCI and NF applications. Nevertheless, inter-individual differences in CS susceptibility should be taken into account for VR-based NF applications.},
}

@article {pmid40048236,
year = {2025},
author = {Zhang, Y and Hedley, FE and Zhang, RY and Jin, J},
title = {Toward quantitative cognitive-behavioral modeling of psychopathology: An active inference account of social anxiety disorder.},
journal = {Journal of psychopathology and clinical science},
volume = {},
number = {},
pages = {},
doi = {10.1037/abn0000972},
pmid = {40048236},
issn = {2769-755X},
support = {//National Key R&D Program of China/ ; //National Natural Science Foundation of China/ ; //Zhejiang University; State Key Laboratory of Brain-Machine Intelligence/ ; //Ministry of Education; Key Laboratory of Brain-Machine Intelligence for Information Behavior/ ; },
abstract = {Understanding psychopathological mechanisms is a central goal in clinical science. While existing theories have demonstrated high research and clinical utility, they have provided limited quantitative explanations of mechanisms. Previous computational modeling studies have primarily focused on isolated factors, posing challenges for advancing clinical theories holistically. To address this gap and leverage the strengths of clinical theories and computational modeling in a synergetic manner, it is crucial to develop quantitative models that integrate major factors proposed by comprehensive theoretical models. In this study, using social anxiety disorder (SAD) as an example, we present a novel approach to formalize conceptual models by combining cognitive-behavioral theory (CBT) with active inference modeling, an innovative computational approach that elucidates human cognition and action. This CBT-informed active inference model integrates multiple mechanistic factors of SAD in a quantitative manner. Through a series of simulations, we systematically examined the effects of these factors on the belief about social threat and tendency of engaging in safety behaviors. The resultant model inherits the conceptual comprehensiveness of CBT and the quantitative rigor of active inference modeling, delineating previously elusive pathogenetic pathways and enabling the formulation of concrete model predictions for future research. Overall, this research presents a novel quantitative model of SAD that unifies major mechanistic factors proposed by CBT and active inference modeling. It highlights the feasibility and potential of integrating clinical theory and computational modeling to advance our understanding of psychopathology. (PsycInfo Database Record (c) 2025 APA, all rights reserved).},
}

@article {pmid40047565,
year = {2025},
author = {Haghighi, P and Jeakle, EN and Sturgill, BS and Abbott, JR and Solis, E and Devata, VS and Vijayakumar, G and Hernandez-Reynoso, AG and Cogan, SF and Pancrazio, JJ},
title = {Enhanced Performance of Novel Amorphous Silicon Carbide Microelectrode Arrays in Rat Motor Cortex.},
journal = {Micromachines},
volume = {16},
number = {2},
pages = {},
doi = {10.3390/mi16020113},
pmid = {40047565},
issn = {2072-666X},
support = {2R01TW104344-22S5/NH/NIH HHS/United States ; },
abstract = {Implantable microelectrode arrays (MEAs) enable the recording of electrical activity from cortical neurons for applications that include brain-machine interfaces. However, MEAs show reduced recording capabilities under chronic implantation conditions. This has largely been attributed to the brain's foreign body response, which is marked by neuroinflammation and gliosis in the immediate vicinity of the MEA implantation site. This has prompted the development of novel MEAs with either coatings or architectures that aim to reduce the tissue response. The present study examines the comparative performance of multi-shank planar, silicon-based devices and low-flexural-rigidity amorphous silicon carbide (a-SiC) MEAs that have a similar architecture but differ with respect to the shank cross-sectional area. Data from a-SiC arrays were previously reported in a prior study from our group. In a manner consistent with the prior work, larger cross-sectional area silicon-based arrays were implanted in the motor cortex of female Sprague-Dawley rats and weekly recordings were made for 16 weeks after implantation. Single unit metrics from the recordings were compared over the implantation period between the device types. Overall, the expression of single units measured from a-SiC devices was significantly higher than for silicon-based MEAs throughout the implantation period. Immunohistochemical analysis demonstrated reduced neuroinflammation and gliosis around the a-SiC MEAs compared to silicon-based devices. Our findings demonstrate that the a-SiC MEAs with a smaller shank cross-sectional area can record single unit activity with more stability and exhibit a reduced inflammatory response compared to the silicon-based device employed in this study.},
}

@article {pmid40046512,
year = {2025},
author = {Fang, K and Wang, Z and Tang, Y and Guo, X and Li, X and Wang, W and Liu, B and Dai, Z},
title = {Dynamically Controlled Flight Altitudes in Robo-Pigeons via Locus Coeruleus Neurostimulation.},
journal = {Research (Washington, D.C.)},
volume = {8},
number = {},
pages = {0632},
pmid = {40046512},
issn = {2639-5274},
abstract = {Robo-pigeons, a novel class of hybrid robotic systems developed using brain-computer interface technology, hold marked promise for search and rescue missions due to their superior load-bearing capacity and sustained flight performance. However, current research remains largely confined to laboratory environments, and precise control of their flight behavior, especially flight altitude regulation, in a large-scale spatial range outdoors continues to pose a challenge. Herein, we focus on overcoming this limitation by using electrical stimulation of the locus coeruleus (LoC) nucleus to regulate outdoor flight altitude. We investigated the effects of varying stimulation parameters, including stimulation frequency (SF), interstimulus interval (ISI), and stimulation cycles (SC), on the flight altitude of robo-pigeons. The findings indicate that SF functions as a pivotal switch controlling the ascending and descending flight modes of the robo-pigeons. Specifically, 60 Hz stimulation effectively induced an average ascending flight of 12.241 m with an 87.72% success rate, while 80 Hz resulted in an average descending flight of 15.655 m with a 90.52% success rate. SF below 40 Hz did not affect flight altitude change, whereas over 100 Hz caused unstable flights. The number of SC was directly correlated with the magnitude of altitude change, enabling quantitative control of flight behavior. Importantly, electrical stimulation of the LoC nucleus had no significant effects on flight direction. This study is the first to establish that targeted variation of electrical stimulation parameters within the LoC nucleus can achieve precise altitude control in robo-pigeons, providing new insights for advancing the control of flight animal-robot systems in real-world applications.},
}

@article {pmid40044089,
year = {2025},
author = {Jialin, A and Zhang, HG and Wang, XH and Wang, JF and Zhao, XY and Wang, C and Cao, MN and Li, XJ and Li, Y and Cao, LL and Zhong, BL and Deng, W},
title = {Cortical activation patterns in generalized anxiety and major depressive disorders measured by multi-channel near-infrared spectroscopy.},
journal = {Journal of affective disorders},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jad.2025.02.116},
pmid = {40044089},
issn = {1573-2517},
abstract = {BACKGROUND: Major depressive disorder (MDD) and generalized anxiety disorder (GAD) are highly prevalent mental disorders in psychiatry, but their overlapping symptoms often complicate precise diagnoses. This study aims to explore differential brain activation patterns in healthy controls (HC), MDD, and GAD groups through functional near-infrared spectroscopy (fNIRS) during the verbal fluency task (VFT) to enhance the accuracy of clinical diagnoses.

METHODS: This study recruited 30 patients with MDD, 45 patients with GAD, and 34 demographically matched HCs. Hemodynamic changes in the prefrontal cortex (PFC) and temporal lobes were measured using a 48-channel fNIRS during the VFT task. Demographics information, clinical characteristics and VFT performance were also recorded.

RESULTS: Compared to HCs, both MDD and GAD share a neurobiological phenotype of hypoactivation in the dorsolateral prefrontal cortex (DLPFC) and medial prefrontal cortex (mPFC) during VFT. Moreover, MDD patients exhibited significantly greater hypoactivation in the left DLPFC and right mPFC than GAD patients.

CONCLUSIONS: Although both GAD and MDD patients exhibit disrupted cortical function, the impairment is less severe in GAD. These findings provide preliminary neurophysiological evidence supporting the utility of the fNIRS-VFT paradigm in differentiating GAD from MDD. This approach may complement traditional diagnostic methods, inform targeted interventions, and ultimately enhance patient outcomes.},
}

@article {pmid40044088,
year = {2025},
author = {Liang, S and Gao, Y and Palaniyappan, L and Song, XM and Zhang, T and Han, JF and Tan, ZL and Li, T},
title = {Transcriptional substrates of cortical thickness alterations in anhedonia of major depressive disorder.},
journal = {Journal of affective disorders},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jad.2025.03.003},
pmid = {40044088},
issn = {1573-2517},
abstract = {BACKGROUND: Anhedonia is a core symptom of major depressive disorder (MDD), which has been shown to be associated with abnormalities in cortical morphology. However, the correlation between cortical thickness (CT) changes with anhedonia in MDD and gene expression remains unclear.

METHODS: We investigated the link between brain-wide gene expression and CT correlates of anhedonia in individuals with MDD, using 7 Tesla neuroimaging and a publicly available transcriptomic dataset. The interest-activity score was used to evaluation MDD with high anhedonia (HA) and low anhedonia (LA). Nineteen patients with HA, nineteen patients with LA, and twenty healthy controls (HC) were enrolled. We investigated CT alterations of anhedonia subgroups relative to HC and related cortical gene expression, enrichment and specific cell types. We further used Neurosynth and von Economo-Koskinas atlas to assess the meta-analytic cognitive functions and cytoarchitectural variation associated with anhedonia-related cortical changes.

RESULTS: Both patient subgroups exhibited widespread CT reduction, with HA manifesting more pronounced changes. Gene expression related to anhedonia had significant spatial correlations with CT differences. Transcriptional signatures related to anhedonia-associated cortical thinning were connected to mitochondrial dysfunction and enriched in adipogenesis, oxidative phosphorylation, mTORC1 signaling pathways, involving neurons, astrocytes, and oligodendrocytes. These CT alterations were significantly correlated with meta-analytic terms involving somatosensory processing and pain perception. HA had reduced CT within the somatomotor and ventral attention networks, and in agranular cortical regions.

LIMITATIONS: These include measuring anhedonia using interest-activity score and employing a cross-sectional design.

CONCLUSIONS: This study sheds light on the molecular basis underlying gene expression associated with anhedonia in MDD, suggesting directions for targeted therapeutic interventions.},
}

@article {pmid40043367,
year = {2025},
author = {Demchenko, I and Shavit, T and Benyamini, M and Zacksenhouse, M},
title = {Self-correcting brain computer interface based on classification of multiple error-related potentials.},
journal = {Journal of neural engineering},
volume = {},
number = {},
pages = {},
doi = {10.1088/1741-2552/adbcda},
pmid = {40043367},
issn = {1741-2552},
abstract = {ObjectiveElectroencephalogram (EEG) based brain-computer interfaces (BCIs) have shown tremendous promise in facilitating direct non-invasive brain-control over external devices. However, their practical application is hampered due to errors in command interpretation. A promising strategy for improving BCI accuracy is based on detecting error-related potentials (ErrPs), which are EEG potentials evoked in response to errors. Thus, performance can be improved by undoing actions that evoke potentials that the BCI detects as ErrPs. To achieve further improvement, we aimed to classify the type of error and correct, rather than just undo, erroneous actions. The objectives of this study are to develop an error classifier (EC) and to investigate the hypothesis that correcting the actions according to the EC decisions improves performance.ApproachTo evaluate our hypothesis we developed a BCI application to control the pose of virtual hands with three possible commands: change the pose of either the right or left hand and maintain pose. Thus, when an action elicits an ErrP, the identity of the correct command is still undecided. The self-correcting BCI included an EC and was developed in three phases: hand control, initial brain control and self-correcting brain control. The first two phases were conducted by 22 participants, and half of them (n=11) also completed the last phase.Main Results Detecting the type of error and correcting actions accordingly improved the success rate of the self-correcting BCI for each participant (n=11), with a significant average improvement of 6.6% and best improvement of 13.5%.Significance Self-correction, based on an EC, was demonstrated to improve the accuracy of BCIs for three commands. Thus, our work presents a significant step toward the development of more reliable and user-friendly non-invasive BCIs.},
}

@article {pmid40043361,
year = {2025},
author = {Susnoschi Luca, I and Vuckovic, A},
title = {How are opposite neurofeedback tasks represented at cortical and corticospinal tract levels?.},
journal = {Journal of neural engineering},
volume = {},
number = {},
pages = {},
doi = {10.1088/1741-2552/adbcdb},
pmid = {40043361},
issn = {1741-2552},
abstract = {The study objective was to characterise indices of learning and patterns of connectivity in two neurofeedback (NF) paradigms that modulate mu oscillations in opposite directions, and the relationship with change in excitability of the corticospinal tract (CST). Approach: Forty-three healthy volunteers participated in 3 NF sessions for upregulation (N=24) or downregulation (N=19) of individual alpha (IA) power at central location Cz. Brain signatures from multichannel electroencephalogram (EEG) were analysed, including oscillatory (power, spindles), non-oscillatory components (Hurst exponent), and effective connectivity (Directed Transfer Function) of participants who were successful at enhancing or suppressing IA power at Cz. CST excitability was studied through leg motor-evoked potential before and after the last NF session. We assessed whether participants modulated widespread alpha or central mu rhythm through the use of current source density derivation (CSD), and related the change in power in mu and upper half of mu band, to CST excitability change. Main results: In the last session, IA/mu power suppression was achieved by 79% of participants, while 63% enhanced IA. CSD-EEG revealed that mu power was upregulated through an increase in the incidence rate of bursts of alpha band activity, while downregulation involved changes in oscillation amplitude and temporal patterns. Neuromodulation also influenced frequencies adjacent to the targeted band, indicating the use of common mental strategies within groups. Directed transfer function analysis showed, for both groups, significant connectivity between structures associated with motor imagery tasks, known to modulate the excitability of the motor cortex, although most connections did not remain significant after correcting for multiple comparisons. CST excitability modulation was related to the absolute amplitude of upper mu modulation, rather than the modulation direction. Significance: The upregulation and downregulation of IA/mu power during NF, with respect to baseline were achieved via distinct mechanisms involving oscillatory and non-oscillatory EEG features. Mu enhancement and suppression post-NF and during the last NF block with respect to the baseline, respectively corresponded to opposite trends in motor-evoked potential changes post-NF. The ability of NF to modulate CST excitability could be a valuable rehabilitation tool for central nervous system disorders (stroke, spinal cord injury), where increased excitability and neural plasticity are desired. This work may inform future neuromodulation protocols and may improve NF training effectiveness by rewarding certain EEG signatures.},
}

@article {pmid40043320,
year = {2025},
author = {Alcolea, PI and Ma, X and Bodkin, KL and Miller, LE and Danziger, ZC},
title = {Less is more: selection from a small set of options improves BCI velocity control.},
journal = {Journal of neural engineering},
volume = {},
number = {},
pages = {},
doi = {10.1088/1741-2552/adbcd9},
pmid = {40043320},
issn = {1741-2552},
abstract = {Decoding algorithms used in invasive brain-computer interfaces (iBCIs) typically convert neural activity into continuously varying velocity commands. We hypothesized that putting constraints on which decoded velocity commands are permissible could improve user performance. To test this hypothesis, we designed the discrete direction selection (DDS) decoder, which uses neural activity to select among a small menu of preset cursor velocities. Approach. We tested DDS in a closed-loop cursor control task against many common continuous velocity decoders in both a human-operated real-time iBCI simulator (the jaBCI) and in a monkey using an iBCI. In the jaBCI, we compared performance across four visits by each of 48 naïve, able-bodied human subjects using either DDS, direct regression with assist (an affine map from neural activity to cursor velocity, DR-A), ReFIT, or the velocity Kalman Filter (vKF). In a follow up study to verify the jaBCI results, we compared a monkey's performance using an iBCI with either DDS or the Wiener filter decoder (a direct regression decoder that includes time history, WF). Main Result. In the jaBCI, DDS substantially outperformed all other decoders with 93% mean targets hit per day compared to DR-A, ReFIT, and vKF with 56%, 39%, and 26% mean targets hit, respectively. With the iBCI, the monkey achieved a 61% success rate with DDS and a 37% success rate with WF. Significance. Discretizing the decoded velocity with DDS effectively traded high resolution velocity commands for less tortuous and lower noise trajectories, highlighting the potential benefits of discretization in simplifying online BCI control. .},
}

@article {pmid40043184,
year = {2025},
author = {Chandler, JA},
title = {Inferring Mental States from Brain Data: Ethico-legal Questions about Social Uses of Brain Data.},
journal = {The Hastings Center report},
volume = {55},
number = {1},
pages = {22-32},
doi = {10.1002/hast.4958},
pmid = {40043184},
issn = {1552-146X},
support = {//ERANET-Neuron Program/ ; /CAPMC/CIHR/Canada ; },
mesh = {Humans ; *Brain ; Privacy/legislation & jurisprudence ; Reproducibility of Results ; },
abstract = {Neurotechnologies that collect and interpret data about brain activity are already in use for medical and nonmedical applications. Refinements of existing noninvasive techniques and the discovery of new ones will likely encourage broader uptake. The increased collection and use of brain data and, in particular, their use to infer the existence of mental states have led to questions about whether mental privacy may be threatened. It may be threatened if the brain data actually support inferences about the mind or if decisions are made about a person in the belief that the inferences are justified. This article considers the chain of inferences lying between data about neural activity and a particular mental state as well as the ethico-legal issues raised by making these inferences, focusing here on what the threshold of reliability should be for using brain data to infer mental states.},
}

Humans
*Brain
Privacy/legislation & jurisprudence
Reproducibility of Results

@article {pmid40043182,
year = {2025},
author = {Yang, Y and Wang, Y and Wang, X},
title = {Harnessing psychedelics for stroke recovery: therapeutic potential and mechanisms.},
journal = {Brain : a journal of neurology},
volume = {},
number = {},
pages = {},
doi = {10.1093/brain/awaf093},
pmid = {40043182},
issn = {1460-2156},
}

@article {pmid40042910,
year = {2025},
author = {Xie, B and Xiong, T and Guo, G and Pan, C and Ma, W and Yu, P},
title = {Bioinspired ion-shuttling memristor with both neuromorphic functions and ion selectivity.},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
volume = {122},
number = {10},
pages = {e2417040122},
doi = {10.1073/pnas.2417040122},
pmid = {40042910},
issn = {1091-6490},
support = {22125406 22074149//MOST | National Natural Science Foundation of China (NSFC)/ ; },
abstract = {The fluidic memristor has attracted growing attention as a promising candidate for neuromorphic computing and brain-computer interfaces. However, a fluidic memristor with ion selectivity as that of natural ion channels remains a key challenge. Herein, inspired by the structure of natural biomembranes, we developed an ion-shuttling memristor (ISM) by utilizing organic solvents and artificial carriers to emulate ion channels embedded in biomembranes, which exhibited both neuromorphic functions and ion selectivity. Pinched hysteresis I-V loop curve, scan rate dependency, and distinctive impedance spectra confirmed the memristive characteristics of the as-prepared device. Moreover, the memory mechanism was discussed theoretically and validated by finite-element modeling. The ISM features multiple neuromorphic functions, such as paired-pulse facilitation, paired-pulse depression, and learning-experience behavior. More importantly, the ion selectivity of the ISM was observed, which allowed further emulation of ion-selective neural functions like resting membrane potential. Benefiting from the structural similarity to membrane-embedded ion channels, the ISM opens the door for ion-based neuromorphic computing and sophisticated chemical regulation by manipulating multifarious ions with neuromorphic functions.},
}

@article {pmid40042891,
year = {2025},
author = {Gielas, AM},
title = {Man, Hibernating Animals, and Poikilothermic: Fish The Present and Future of BCI Technology.},
journal = {Journal of special operations medicine : a peer reviewed journal for SOF medical professionals},
volume = {},
number = {},
pages = {},
doi = {10.55460/FA29-NVKE},
pmid = {40042891},
issn = {1553-9768},
abstract = {In 2024 and early 2025, several successful surgeries involving brain-computer interfaces (BCIs) gained media attention, including those conducted by Elon Musk's company Neuralink, which implanted BCIs in three paralyzed volunteers, allowing them to control computers through thought alone. While the concept of merging humans with machines dates back to the 1960s, BCI technology has now entered the clinical trial stage, with a focus on restoring communication, mobility, and sensation in individuals with severe disabilities and neurodegenerative disorders. For over two decades, BCIs have also been explored as tools to enhance the cognitive and physical abilities of military personnel. However, before Special Operations Forces (SOF) medical staff encounter BCIs in an enhancement capacity, they are likely to first come across them in medical settings. This article provides an overview of BCI technology, focusing on 1) how it works, 2) its potential significance for injured SOF servicemembers, 3) current challenges, and 4) its potential to enhance SOF in the future.},
}

@article {pmid40040918,
year = {2025},
author = {Jiang, Y and Liu, YL and Zhou, X and Shu, QQ and Dong, L and Xu, Z and Wan, JQ},
title = {A retrospective study of the Dual-channels Bolus Contrast Injection (Dc-BCI) technique during endovascular mechanical thrombectomy in the management of acute ischemic stroke due to large-vessel occlusion: a technical report.},
journal = {Frontiers in neurology},
volume = {16},
number = {},
pages = {1508976},
pmid = {40040918},
issn = {1664-2295},
abstract = {Endovascular mechanical thrombectomy (EMT) is an effective treatment for acute ischemic stroke and identifying the precise thrombus size remains key to a successful EMT. However, no imaging modality has been able to provide this information simultaneously and efficiently in an emergency setting. The present study introduces a novel technique named dual-channel bolus contrast injection (Dc-BCI) for determining thrombus size and location during EMT. In the in vitro study, the Dc-BCI demonstrated an accurate projection of the thrombus size, as the actual thrombus diameter (R[2] = 0.92, p < 0.01) and length (R[2] = 0.94, p < 0.01) exhibited a high degree of correlation with that of obtained from Dc-BCI. Consequently, between February 2023 and August 2024, 87 patients diagnosed with acute cerebral large vessel occlusions were enrolled in the study and received EMT for the treatment of acute cerebral large vessel occlusions. The Dc-BCI was successfully performed in all patients to measure the diameter and length of the thrombus. These information were used to select an appropriate stent-retriever for EMT. The restoration of blood flow was achieved in 84 patients (96.6%) to an mTICI score of 2b/3. Additionally, a low incidence of postoperative complications was observed (e.g., subarachnoid hemorrhage 8% and cerebral hemorrhage 5.7%). In conclusion, it can be posited that the Dc-BCI has the potential to enhance the outcomes of EMT, as it is capable of revealing the thrombus size information, which optimizes the interaction between the stent retriever and the thrombus, while simultaneously reducing the risk of vascular injury that is associated with the prolonged use of the stent retriever.},
}

@article {pmid40040909,
year = {2025},
author = {Tekin, U and Dener, M},
title = {A bibliometric analysis of studies on artificial intelligence in neuroscience.},
journal = {Frontiers in neurology},
volume = {16},
number = {},
pages = {1474484},
pmid = {40040909},
issn = {1664-2295},
abstract = {The incorporation of artificial intelligence (AI) into neuroscience has the potential to significantly enhance our comprehension of brain function and facilitate more effective diagnosis and treatment of neurological disorders. Artificial intelligence (AI) techniques, particularly deep learning and machine learning, offer transformative solutions by improving the analysis of complex neural data, facilitating early diagnosis, and enabling personalized treatment approaches. A bibliometric analysis is a method that employs quantitative techniques for the examination of scientific literature, with the objective of identifying trends in research, evaluating the impact of influential studies, and mapping the networks of collaboration. In light of the accelerated growth and interdisciplinary scope of AI applications in neuroscience, a bibliometric analysis is vital for mapping the landscape, identifying pivotal contributions, and underscoring emerging areas of interest. This study aims to address this need by examining 1,208 studies published between 1983 and 2024 from the Web of Science database. The analysis reveals a notable surge in publications since the mid-2010s, with substantial advancements in neurological imaging, brain-computer interfaces (BCI), and the diagnosis and treatment of neurological diseases. The analysis underscores the pioneering role of countries such as the United States, China, and the United Kingdom in this field and highlights the prevalence of international collaboration. This study offers a comprehensive overview of the current state and future directions of AI applications in neuroscience, as well as an examination of the transformative potential of AI in advancing neurological research and healthcare. It is recommended that future research address the ethical issues, data privacy concerns, and interpretability of AI models in order to fully capitalize on the benefits of AI in neuroscience.},
}

@article {pmid40040811,
year = {2025},
author = {Feng, X and Bao, X and Huang, H and Wang, Z and Hu, W and Xue, C and Song, Z and Cai, Y and Huang, Q and Li, Y},
title = {Frontal gamma-alpha ratio reveals neural oscillatory mechanism of attention shifting in tinnitus.},
journal = {iScience},
volume = {28},
number = {3},
pages = {111929},
pmid = {40040811},
issn = {2589-0042},
abstract = {In clinical practice, the symptoms of tinnitus patients can be temporarily alleviated by diverting their attention away from disturbing sounds. However, the precise mechanisms through which this alleviation occurs are still not well understood. Here, we aimed to directly evaluate the role of attention in tinnitus alleviation by conducting distraction tasks with multilevel loads and resting-state tests among 52 adults with tinnitus and 52 healthy controls. We demonstrated that the abnormal neural oscillations in tinnitus subjects, reflected in an altered gamma/alpha ratio index in the frontal lobe, could be regulated by attention shifting in a linear manner for which the regulatory effect increased with the load of distraction. Quantitative measures of the regulation significantly correlated with symptom severity. Altogether, our work provides proof-of-concept for the role of attention in tinnitus perception and lays a solid foundation to support evidence-based applications of attention shifting in clinical interventions for tinnitus.},
}

@article {pmid40040231,
year = {2024},
author = {Chaudhry, ZA and Baxter, RH and Fu, JL and Wang, PT and Sohn, WJ and Do, AH},
title = {Feasibility of Immersive Virtual Reality Feedback for Enhancing Learning in Brain-Computer Interface Control of Ambulation.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782667},
pmid = {40040231},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Virtual Reality ; *Walking/physiology ; *Electroencephalography ; Male ; Adult ; Feasibility Studies ; Learning ; Female ; Young Adult ; Spinal Cord Injuries/rehabilitation/physiopathology ; User-Computer Interface ; },
abstract = {After prolonged paralysis, paraplegic spinal cord injury (SCI) patients typically lose the ability to generate the expected electroencephalogram (EEG) α/β modulation associated with leg movements. Brain computer interface (BCI)-controlled ambulation devices have emerged as a way to restore brain-controlled walking, but this loss of EEG signal modulation may impede the ability to operate such systems and prolonged training may be necessary to restore this physiologic phenomenon. To address this issue, this study explores the use of immersive virtual reality (VR) in providing more convincing feedback to enhance learning within a BCI training paradigm. Here, an EEG-based BCI-controlled walking simulator with an environment composed of 10 designated stop zones along a linear course was used to test this concept. Able-bodied subjects were tasked with using idling or kinesthetic motor imagery (KMI) of gait to control an avatar to either dwell at each designated stop for 5 s or advance along the course respectively. Subject performance was measured using a composite score per run and learning rate across runs. Composite scores were calculated as the geometric mean of two subscores: a stop score (reflecting the number of successful stops), and a time score (reflecting how fast the course was completed). The learning rate was calculated as the slope of the composite scores across all runs. A random walk procedure was performed to determine the statistical likelihood that each BCI run was purposeful (p≤ 0.001). Three able-bodied subjects were recruited (2 in immersive VR group and 1 in non-immersive VR group), and operated the simulator for up to 4 separate visits. The immersive VR group achieved an average composite score of 60.4% ± 12.9, while the non-VR group had an average composite score of 79.0% ± 12.2. The learning rate was 1.07%/run and 0.42%/run for the immersive and non-immersive VR groups, respectively. Purposeful control was attained in a higher proportion of runs for the immersive VR group than in the non-immersive VR group. Although limited by small sample size, this study demonstrates a conceptual framework of implementing immersive VR feedback using more convincing sensory feedback to aid training with BCI devices. Future work will test this protocol in SCI patients and with larger sample size.},
}

Humans
*Brain-Computer Interfaces
*Virtual Reality
*Walking/physiology
*Electroencephalography
Male
Adult
Feasibility Studies
Learning
Female
Young Adult
Spinal Cord Injuries/rehabilitation/physiopathology
User-Computer Interface

@article {pmid40040213,
year = {2024},
author = {Okitsu, K and Isezaki, T and Obara, K and Nishimura, Y},
title = {Enhancing Brain Machine Interface Decoding Accuracy through Domain Knowledge Integration.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782166},
pmid = {40040213},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Animals ; Macaca mulatta ; Muscle, Skeletal/physiology ; Algorithms ; Humans ; },
abstract = {This paper introduces a novel decoding approach for Brain Machine Interface (BMI) that enhances the estimation accuracy and stability of muscle activity by incorporating domain knowledge of motor control. Our approach uniquely integrates domain knowledge, focusing on the relationship between torque direction and muscle activity in isometric wrist tasks. We demonstrate the effectiveness of our approach through decoding analysis with non-human primates performing a wrist torque tracking task. By implementing a Kalman filter augmented with models of muscle activity and torque for specific movement directions, we show significant improvements compared to vanilla Kalman filter in the accuracy of muscle activity estimation. The proposed approach presents a promising direction for enhancing the performance of BMI by leveraging domain-specific insights into motor control.},
}

*Brain-Computer Interfaces
Animals
Macaca mulatta
Muscle, Skeletal/physiology
Algorithms
Humans

@article {pmid40040208,
year = {2024},
author = {Li, D and Shin, HB and Yin, K and Lee, SW},
title = {Domain-Incremental Learning Framework for Continual Motor Imagery EEG Classification Task.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10781886},
pmid = {40040208},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Brain-Computer Interfaces ; Imagination/physiology ; Machine Learning ; Algorithms ; Signal Processing, Computer-Assisted ; },
abstract = {Due to inter-subject variability in electroencephalogram (EEG) signals, the generalization ability of many existing brain-computer interface (BCI) models is significantly limited. Although transfer learning (TL) offers a temporary solution, in scenarios requiring sustained knowledge transfer, the performance of TL-based models gradually declines as the number of transfers increases-a phenomenon known as catastrophic forgetting. To address this issue, we introduce a novel domain-incremental learning framework for the continual motor imagery (MI) EEG classification. Specifically, to learn and retain common features between subjects, we separate latent representations into subject-invariant and subject-specific features through adversarial training, while also proposing an extensible architecture to preserve features that are easily forgotten. Additionally, we incorporate a memory replay mechanism to reinforce previously acquired knowledge. Through extensive experiments, we demonstrate our framework's effectiveness in mitigating forgetting within the continual MI-EEG classification task.},
}

*Electroencephalography/methods
Humans
*Brain-Computer Interfaces
Imagination/physiology
Machine Learning
Algorithms
Signal Processing, Computer-Assisted

@article {pmid40040206,
year = {2024},
author = {Huang, CM and Lai, WL and Yang, CC and Hsieh, YJ and Wu, CM and Lee, CH},
title = {EEG Channel Localization and Selection via Training with Noise Injection for BCI Applications.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782774},
pmid = {40040206},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Brain-Computer Interfaces ; *Algorithms ; Signal Processing, Computer-Assisted ; Signal-To-Noise Ratio ; },
abstract = {Electroencephalography (EEG) is crucial for monitoring brain activity in neuroscience and clinical applications. However, the multitude of channels recorded by scalp electrodes poses challenges, including impractical usage and high model complexity. This paper addresses the challenges of high dimensionality in EEG data and introduces an innovative EEG channel selection algorithm, LSvT-NI, based on model training and noise injection, achieving substantial reductions in channels, model size, and complexity while maintaining high classification accuracy. Validated through experiments on EEGNet and the BCI Competition IV 2a dataset, the algorithm proves beneficial for practical and cost-efficient scenarios. Specifically, experiments on the BCI Competition IV 2a dataset demonstrate that LSvT-NI with white noise and pink noise at 5dB SNR achieves a remarkable 77.3% and 72.7% reduction in channels, along with 11.7% and 11% reductions in model size, and 86.9% and 71.8% in computation complexity.},
}

*Electroencephalography/methods
Humans
*Brain-Computer Interfaces
*Algorithms
Signal Processing, Computer-Assisted
Signal-To-Noise Ratio

@article {pmid40040181,
year = {2024},
author = {Sartipi, S and Cetin, M},
title = {Robust EEG-based Emotion Recognition Using an Inception and Two-sided Perturbation Model.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782060},
pmid = {40040181},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Emotions/physiology ; Brain-Computer Interfaces ; Signal Processing, Computer-Assisted ; Algorithms ; Deep Learning ; },
abstract = {Automated emotion recognition using electroencephalogram (EEG) signals has gained substantial attention. Although deep learning approaches exhibit strong performance, they often suffer from vulnerabilities to various perturbations, like environmental noise and adversarial attacks. In this paper, we propose an Inception feature generator and two-sided perturbation (INC-TSP) approach to enhance emotion recognition in brain-computer interfaces. INC-TSP integrates the Inception module for EEG data analysis and employs two-sided perturbation (TSP) as a defensive mechanism against input perturbations. TSP introduces worst-case perturbations to the model's weights and inputs, reinforcing the model's elasticity against adversarial attacks. The proposed approach addresses the challenge of maintaining accurate emotion recognition in the presence of input uncertainties. We validate INC-TSP in a subject-independent three-class emotion recognition scenario, demonstrating robust performance.},
}

Humans
*Electroencephalography/methods
*Emotions/physiology
Brain-Computer Interfaces
Signal Processing, Computer-Assisted
Algorithms
Deep Learning

@article {pmid40040170,
year = {2024},
author = {Meng, J and Yang, M and Zhang, S and Xu, M and Meng, L and Ming, D},
title = {An online brain-computer interface for a precise positioning of target based on rapid serial visual presentation.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782815},
pmid = {40040170},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Male ; Adult ; Female ; Young Adult ; Evoked Potentials/physiology ; Brain/physiology ; Photic Stimulation ; },
abstract = {The brain-computer interface (BCI) based on rapid serial visual presentation (RSVP) provides a novel approach for efficiently optimizing traditional machine-based target detection, revealing a broad application prospect in security, entrainment, monitoring, etc. A bottleneck of current RSVP-BCI is that its detectable result is limited to a binary way, i.e., target vs. non-target, more detailed and important information about targets, such as the precise position, remains undetectable. To solve this problem, this study investigated the relationship between targets positions (up, down, left, right) and electroencephalogram (EEG) characteristics, and tested the separability of EEGs induced by the four targets positions in an online RSVP-BCI. Twelve healthy subjects participated in this study, event-related potential (ERP), topographies, laterality index (LI), discriminant canonical pattern matching (DCPM) methods were used to analyzed the EEG data. Consequently, left-right targets induced ipsilateral ERPs between bilateral hemispheres; when targets appeared at up and down positions, opposite ERPs were found between frontal and occipital areas; up-down and left-right difference reached its maximum in the 140~190ms and 190~240ms temporal window, respectively. Single-trial classification showed five-class balanced accuracy (BACC) (non-target, target at up/ down/ left/ right position) was 71.02% and 67.91% for offline and online sessions, respectively. The results provide new understanding of the RSVP features for developing BCIs.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Male
Adult
Female
Young Adult
Evoked Potentials/physiology
Brain/physiology
Photic Stimulation

@article {pmid40040166,
year = {2024},
author = {Zhuo, F and Lv, B and Tang, F},
title = {Time Window Optimization for Riemannian Geometry-based Motor Imagery EEG Classification.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782640},
pmid = {40040166},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Brain-Computer Interfaces ; Algorithms ; Signal Processing, Computer-Assisted ; Imagination/physiology ; },
abstract = {The existing Riemannian geometry-based approaches for brain computer interface (BCI) employ fixed time windows. However, the inherent variability and dynamic changes among subjects necessitate robust and adaptive solutions for time window optimization. Recognizing the current limitations of Riemannian classifiers, we propose a time window selection confidence metric (TWSCM) based on Riemannian geometry. This metric operates on the manifold of symmetric positive definite (SPD) matrices, providing a theoretically grounded and computationally efficient approach for time window optimization. The optimization process is unsupervised, which is able to deal with the online scenario without training labels. Experimental results on the BCI competition IV dataset IIa demonstrate that the classification performance is significantly improved for most subjects. The average performance over six subjects improved by 7.52%. The simulated online experiment shows enhanced performance in comparison to baseline experiments without time window optimization. Additionally, an in-depth analysis of TWSCM provides insights into performance variations among subjects. Overall, this paper introduces the first time window optimization method within the Riemannian geometric framework, presenting an effective and interpretable approach for optimizing time windows in motor imagery classification, providing a novel and promising perspective in EEG signal analysis.},
}

Humans
*Electroencephalography/methods
*Brain-Computer Interfaces
Algorithms
Signal Processing, Computer-Assisted
Imagination/physiology

@article {pmid40040155,
year = {2024},
author = {Huang, J and Tostado-Marcos, P and Narasimha, SM and Patel, AN and Arneodo, EM and Gentner, TQ and Mishne, G and Gilja, V},
title = {Guiding Brain-to-Vocalization Decoder Design Using Structured Generalization Error.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782761},
pmid = {40040155},
issn = {2694-0604},
mesh = {Animals ; *Finches/physiology ; *Vocalization, Animal/physiology ; Humans ; Brain/physiology ; Brain-Computer Interfaces ; Speech/physiology ; },
abstract = {State-of-the-art intracortical neuroprostheses currently enable communication at 60+ words per minute for anarthric individuals by training on over 10K sentences to account for phoneme variability in different word contexts. There is limited understanding about whether this performance can be maintained in decoding naturalistic speech with 40K+ word vocabularies across elicited, spontaneous, and conversational speech contexts. We introduce a vocal-unit-level generalization test to explicitly evaluate neural decoder performance with an expanded and more diverse behavioral repertoire. Tested on neural decoders modeling zebra finch vocalization, an analog to human vocal production, we compare three decoders with different input types: spike trains, neural factors, and firing rates. The factors and rates are latent neural features inferred using trained Latent Factor Analysis via Dynamical Systems (LFADS) models that capture the population neural dynamics during vocal production. While the conventional random holdout generalization error measure is similar for all three decoders, factor- and rate-based decoders outperform spike-based decoders when testing vocal-unit-holdout generalization error. These results suggest the later models better adapt to flexible vocalization inference when trained with partial observation of data variation, motivating further exploration of decoders incorporating latent neural and vocalization dynamics.},
}

Animals
*Finches/physiology
*Vocalization, Animal/physiology
Humans
Brain/physiology
Brain-Computer Interfaces
Speech/physiology

@article {pmid40040137,
year = {2024},
author = {Idowu, OP and Kinney-Lang, E and Gulamhusein, A and Irvine, B and Kirton, A and Abou-Zeid, H},
title = {Profiling a Raspberry Pi-Based Motor Imagery Classification to Facilitate At-Home BCI for Children with Disabilities.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-7},
doi = {10.1109/EMBC53108.2024.10781873},
pmid = {40040137},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; Child ; *Children with Disabilities/rehabilitation ; Neural Networks, Computer ; Imagination/physiology ; Electroencephalography/methods ; Machine Learning ; },
abstract = {There has been incremental progress in moving BCI out of the laboratory environment and into the homes of those who would benefit most, especially children living with severe physical disabilities. Practical issues, such as available computational resources and long calibration times, have slowed down the adoption of such systems. To develop an efficient and scalable machine learning framework consistent with early approaches that facilitate at-home BCI use, this study provides valuable insights into measuring the behavioral characteristics of a Raspberry Pi 4 (RPi4) during the operation and execution of standard BCI processes, including the training and evaluation of classifier models. The results, which evaluated ten standard classifiers, including the Riemannian Geometry (RG) framework and more advanced deep learning approaches like Artificial Neural Network (ANN), were profiled on RPi4. These were compared to Desktop and MacBook computations for metrics such as training time, inference time, peak memory, and incremental memory usage, with computational bottlenecks identified. Our assessment revealed comparable performance metrics (84.3% of accuracy, recall, and f1_score, and 84.7% precision) for the neural network models despite the lower computational resources. Profiling results, including 1.74 sec training time, 0.405 sec inference time, 1154.9 MiB peak memory, and 405.2 MiB incremental memory usage, also demonstrated that the RPi4 is a potentially viable device for low-cost BCI systems. However, high-resource demanding classifiers such as ANN may need to be carefully considered in their implementation, which, in turn, will scale down the potential cost and complexity of adopting practical, impactful at-home BCI systems.},
}

Humans
*Brain-Computer Interfaces
Child
*Children with Disabilities/rehabilitation
Neural Networks, Computer
Imagination/physiology
Electroencephalography/methods
Machine Learning

@article {pmid40040110,
year = {2024},
author = {Wang, Z and Liu, Y and Wu, W and Huang, S and An, X and Ming, D},
title = {EEG Pattern Comparison and Classification Performance of Motor Imagery Between Supernumerary and Inherent Limbs.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782967},
pmid = {40040110},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Imagination/physiology ; Brain-Computer Interfaces ; Male ; Adult ; Movement/physiology ; Robotics ; Female ; Young Adult ; },
abstract = {Adding supernumerary robotic limbs (SRLs) to humans and controlling them directly through the brain are main goals for movement augmentation. However, whether neural patterns that are distinct from the traditional inherent limbs motor imagery (MI) paradigm can be extracted, which is essential for the high-dimensional control of external equipment. In this study, a novel type of MI paradigm based on SRLs was proposed, consisting of "the sixth-finger", "the third-arm" and "the third-leg", and validated the distinctness of EEG response patterns between the novel and the traditional (hand, arm and leg) MI paradigm. The results showed that imagining extra limbs induced more obvious event-related desynchronization (ERD) phenomenon in sensorimotor areas compared to imagining inherent limbs. Classification results indicate well separable performance among different mental tasks (all above 86%, with a maximum of 90.5%). This work proposed a novel type of MI paradigm, and offered new way for widening the control bandwidth of the BCI system.},
}

Humans
*Electroencephalography/methods
*Imagination/physiology
Brain-Computer Interfaces
Male
Adult
Movement/physiology
Robotics
Female
Young Adult

@article {pmid40040096,
year = {2024},
author = {Lim, EY and Yin, K and Shin, HB and Lee, SW},
title = {Baseline-Guided Representation Learning for Noise-Robust EEG Signal Classification.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781970},
pmid = {40040096},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Brain-Computer Interfaces ; *Signal Processing, Computer-Assisted ; Deep Learning ; Algorithms ; Signal-To-Noise Ratio ; },
abstract = {Brain-computer interfaces (BCIs) suffer from limited accuracy due to noisy electroencephalography (EEG) signals. Existing denoising methods often remove artifacts such as eye movement or use techniques such as linear detrending, which inadvertently discard crucial task-relevant information. To address this issue, we present BGNet, a novel deep learning framework that leverages underutilized baseline EEG signals for dynamic noise mitigation and robust feature extraction to improve motor imagery (MI) EEG classification. Our approach employs data augmentation to strengthen model robustness, an autoencoder to extract features from baseline and MI signals, a feature alignment module to separate specific task and noise, and a classifier. We achieve state-of-the-art performance, an improvement of 5.9% and 3.7% on the BCIC IV 2a and 2b datasets, respectively. The qualitative analysis of our learned features proves superior representational power over baseline models, a critical aspect in dealing with noisy EEG signals. Our findings demonstrate the efficacy of readily available baseline signals in enhancing performance, opening possibilities for simplified BCI systems in brain-based communication applications.},
}

*Electroencephalography/methods
Humans
*Brain-Computer Interfaces
*Signal Processing, Computer-Assisted
Deep Learning
Algorithms
Signal-To-Noise Ratio

@article {pmid40040056,
year = {2024},
author = {Huang, S and Liu, Y and Xu, W and Wang, Z and Ming, D},
title = {Enhancement of Functional Connectivity in Frontal-Parietal Regions After BCI-Actuated Supernumerary Robotic Finger Training.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781807},
pmid = {40040056},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Fingers/physiology ; Male ; *Robotics ; *Parietal Lobe/physiology/diagnostic imaging ; *Frontal Lobe/physiology/diagnostic imaging ; Magnetic Resonance Imaging ; Adult ; Female ; Young Adult ; },
abstract = {The supernumerary robotic finger (SRF) can expand human hand abilities to achieve motor augmentation, and integrate with brain computer interface (BCI) to free the occupation of inherent body degrees of freedom. However, the neuro remodeling mechanisms of brain-actuated SRF training is not clear. In this study, a BCI-actuated SRF was used to investigate the concurrent changes in behavior and brain activity. After 4 weeks BCI-SRF training, the novel sequence operation accuracy rate enhanced by more than 350% compared with innate finger training (IFT). Task-based fMRI showed a significant increase in lateral activation of sensorimotor cortex and found a significant activation change in S1M1_L area. Moreover, BCI-SRF training significantly increase functional connectivity (FC) between S1M1_L and Frontal_Mid_L compared with IFT at post stage. And this FC increase in frontal-parietal is also significant at post vs pre in BCI-SRF group and significantly correlated with the improvement of motor sequence accuracy rate. Our findings provide useful insights into the enhanced human-machine interaction and this efficacy exhibited significant potential for clinical rehabilitation application.},
}

Humans
*Brain-Computer Interfaces
*Fingers/physiology
Male
*Robotics
*Parietal Lobe/physiology/diagnostic imaging
*Frontal Lobe/physiology/diagnostic imaging
Magnetic Resonance Imaging
Adult
Female
Young Adult

@article {pmid40040035,
year = {2024},
author = {Norouzi, M and Amirani, MZ and Shahriari, Y and Abiri, R},
title = {Precision Enhancement in Sustained Visual Attention Training Platforms: Offline EEG Signal Analysis for Classifier Fine-Tuning.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782784},
pmid = {40040035},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Attention/physiology ; *Brain-Computer Interfaces ; *Support Vector Machine ; *Signal Processing, Computer-Assisted ; Adult ; Male ; Female ; Young Adult ; },
abstract = {In this study, a novel open-source brain-computer interface (BCI) platform was developed to decode scalp electroencephalography (EEG) signals associated with sustained attention. The EEG signal collection was conducted using a wireless headset during a sustained visual attention task, where participants were instructed to discriminate between composite images superimposed with scenes and faces, responding only to the relevant subcategory while ignoring the irrelevant ones. Seven volunteers participated in this experiment. The data collected were subjected to analyses through event-related potential (ERP), Hilbert Transform, and Wavelet Transform to extract temporal and spectral features. For each participant, utilizing its extracted features, personalized Support Vector Machine (SVM) and Random Forest (RF) models with tuned hyperparameters were developed. The models aimed to decode the participant's attentional state towards the face and scene stimuli. The SVM models achieved a higher average accuracy of 80% and an Area Under the Curve (AUC) of 0.86, while the RF models showed an average accuracy of 78% and AUC of 0.8. This work suggests potential applications for the evaluation of visual attention and the development of closed-loop brainwave regulation systems in the future.},
}

Humans
*Electroencephalography/methods
*Attention/physiology
*Brain-Computer Interfaces
*Support Vector Machine
*Signal Processing, Computer-Assisted
Adult
Male
Female
Young Adult

@article {pmid40040033,
year = {2024},
author = {Ferdous, TR and Pollonini, L and Francis, JT},
title = {Enhancing Auditory BCI Performance: Incorporation of Connectivity Analysis.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782147},
pmid = {40040033},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Support Vector Machine ; Brain/physiology/diagnostic imaging ; Acoustic Stimulation ; },
abstract = {Brain connectivity analysis to classify auditory stimuli applicable to invasive auditory BCI technology, particularly intracranial electroencephalography (iEEG) remains an exciting frontier. This study revealed insights into brain network dynamics, improving analysis precision to distinguish related auditory stimuli such as speech and music. We thereby contribute to advancing auditory BCI systems to bridge the gap between noninvasive and invasive BCI by utilizing noninvasive BCI methodological frameworks to invasive BCI (iEEG) data. We focused on the viability of using connectivity matrices in BCI calculated across brain waves such as alpha, beta, theta, and gamma. The research highlights that the traditional machine learning classifier, Support Vector Machine (SVM), demonstrates exceptional capabilities in handling brain connectivity data, exhibiting an outstanding 97% accuracy in classifying brain states, surpassing previous relevant studies with an improvement of 9.64% The results are significant as we show that neural activity in the gamma band provides the best classification performance using connectivity matrices calculated with Phase Locking Values and Coherence methods.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Support Vector Machine
Brain/physiology/diagnostic imaging
Acoustic Stimulation

@article {pmid40040032,
year = {2024},
author = {Veeranki, YR and Posada-Quintero, HF},
title = {High-Resolution Time-Frequency Analysis of EEG Signals for Affective Computing.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782482},
pmid = {40040032},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Signal Processing, Computer-Assisted ; *Algorithms ; Brain-Computer Interfaces ; Male ; Female ; Brain/physiology ; Adult ; Emotions/physiology ; },
abstract = {Affective computing is a critical aspect of human-computer interaction. Electroencephalographic (EEG) signals, which reflect electrical brain activity, are widely used for the understanding of human emotional states. However, these signals are nonlinear and nonstationary, making traditional analysis methods insufficient. To address these challenges, recent studies have focused on time-frequency analysis. In this paper, we propose a variable frequency complex demodulation (VFCDM) approach to obtain high-resolution time-frequency spectra (TFS) from EEG signals. First, we compute the TFS using the time-varying optimal parameter search technique to capture the spectral information. Then we generate VFCDM sub-bands and extract statistical features from each of the sub-bands. These features are then used with the Random Forest algorithm to classify arousal and valence dimensions. Our results demonstrate the robustness of this approach and its ability to accurately discriminate complex affective dimensions. The δ-VFCDM and γ-VFCDM bands produced the highest F1 scores of 71.80% for Arousal and 69.55% for Valence differentiation. This work significantly advances EEG-based affective computing and opens avenues for more emotionally attuned human-computer interaction systems.},
}

Humans
*Electroencephalography/methods
*Signal Processing, Computer-Assisted
*Algorithms
Brain-Computer Interfaces
Male
Female
Brain/physiology
Adult
Emotions/physiology

@article {pmid40039972,
year = {2024},
author = {Ye, H and Goerttler, S and He, F},
title = {EEG-GMACN: Interpretable EEG Graph Mutual Attention Convolutional Network.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782694},
pmid = {40039972},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Signal Processing, Computer-Assisted ; *Neural Networks, Computer ; Electrodes ; Algorithms ; Brain/physiology ; Brain-Computer Interfaces ; },
abstract = {Electroencephalogram (EEG) is a valuable technique to record brain electrical activity through electrodes placed on the scalp. Analyzing EEG signals contributes to the understanding of neurological conditions and developing brain-computer interface. Graph Signal Processing (GSP) has emerged as a promising method for EEG spatial-temporal analysis, by further considering the topological relationships between electrodes. However, existing GSP studies lack interpretability of electrode importance and the credibility of prediction confidence. This work proposes an EEG Graph Mutual Attention Convolutional Network (EEG-GMACN), by introducing an 'Inverse Graph Weight Module' to output interpretable electrode graph weights, enhancing the clinical credibility and interpretability of EEG classification results. Additionally, we incorporate a mutual attention mechanism module into the model to improve its capability to distinguish critical electrodes and introduce credibility calibration to assess the uncertainty of prediction results. This study enhances the transparency and effectiveness of EEG analysis, paving the way for its widespread use in clinical and neuroscience research.},
}

*Electroencephalography/methods
Humans
*Signal Processing, Computer-Assisted
*Neural Networks, Computer
Electrodes
Algorithms
Brain/physiology
Brain-Computer Interfaces

@article {pmid40039945,
year = {2024},
author = {Kanda, T and Isezaki, T and Okitsu, K},
title = {A Study on Changes in Estimation Accuracy for EEG Data During Calibration and Operation in MI-BCI.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782616},
pmid = {40039945},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Calibration ; Male ; Female ; Adult ; Young Adult ; Signal Processing, Computer-Assisted ; Imagination/physiology ; Deep Learning ; },
abstract = {Changes in psychological factors have been suggested to cause variations in brain-computer interface (BCI) performance. More specifically, differences in psychological variables between the calibration and operation phases may cause a decrease in accuracy during operation, presenting a potential challenge for the adoption of BCI technology. The purpose of this study is to analyze the differences in accuracy between the calibration and operation phases of a BCI using a deep learning model. We structured tasks to simulate the calibration and operation phases, and participants performed motor imagery tasks under both conditions. The analysis revealed a significant decrease in accuracy for data obtained under the operation condition, highlighting the need for techniques capable of adapting to the electroencephalography signal data produced when users execute operations.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Calibration
Male
Female
Adult
Young Adult
Signal Processing, Computer-Assisted
Imagination/physiology
Deep Learning

@article {pmid40039943,
year = {2024},
author = {Wang, J and Li, X and Huang, Y and Xiao, D and Fan, Y and Huang, W and Hu, Y},
title = {Patient-Involved Validation of A Somatosensory ERP-BCI Facilitated by Electric Stimulation for Stroke Rehabilitation.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-6},
doi = {10.1109/EMBC53108.2024.10781706},
pmid = {40039943},
issn = {2694-0604},
mesh = {Humans ; *Stroke Rehabilitation/methods ; *Brain-Computer Interfaces ; Male ; Electroencephalography/methods ; Electric Stimulation/methods ; Female ; Evoked Potentials, Somatosensory/physiology ; Adult ; },
abstract = {Brain-computer interface (BCI) is emerging as an effective complementary solution in the field of rehabilitation for the interaction between patients and robotic assistive devices. Specifically, the somatosensory event-related potentials (ERP) BCI has unique advantage for post-stroke motor rehabilitation scenarios and has been proven feasible on healthy subjects. We conducted the first patient-involved somatosensory ERP-BCI experiment with electric stimulation to evaluate its feasibility for real-world clinical usage. In the experiment, participant selectively attended to electric stimuli applied on either left or right wrist, which represented the operation of robot-assisted exercise of corresponding hand. An integrated platform that included exercise, stimulation, and electroencephalography (EEG) sampling modules was used. For evaluation, we used convolutional neural network (CNN) with transformer module to construct subject-specific intent decoder. The network demonstrated on average 58.95% accuracy in classifying target response from a single ERP trial. When using the classification from multiple consecutive trials, the decoder achieved a maximum of 80.12% mean accuracy in recognizing participants intent, and the highest rate from a single participant was 97.21%. The best information transfer rate (ITR) achieved was 1.956 Bit/min. These results demonstrated that the proposed BCI paradigm could be a valid choice for stroke rehabilitation. In the next stage, we anticipate the involvement of larger patient population, real-time feedback training, and the subsequent quantified motor function recovery results.},
}

Humans
*Stroke Rehabilitation/methods
*Brain-Computer Interfaces
Male
Electroencephalography/methods
Electric Stimulation/methods
Female
Evoked Potentials, Somatosensory/physiology
Adult

@article {pmid40039935,
year = {2024},
author = {Han, HT and Kim, SJ and Lee, DH and Lee, SW},
title = {Proxy-based Masking Module for Revealing Relevance of Characteristics in Motor Imagery.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782698},
pmid = {40039935},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; *Imagination/physiology ; Movement/physiology ; Signal Processing, Computer-Assisted ; Algorithms ; },
abstract = {Brain-computer interface (BCI) has been developed for communication between users and external devices by reflecting users' status and intentions. Motor imagery (MI) is one of the BCI paradigms for controlling external devices by imagining muscle movements. MI-based EEG signals generally tend to contain signals with sparse MI characteristics (sparse MI signals). When conducting domain adaptation (DA) on MI signals with sparse MI signals, it could interrupt the training process. In this paper, we proposed the proxy-based masking module (PMM) for masking sparse MI signals within MI signals. The proposed module was designed to suppress the amplitude of sparse MI signals using the negative similarity-based mask generated between the proxy of rest signals and the feature vectors of MI signals. We attached our proposed module to the conventional DA methods (i.e., the DJDAN, the MAAN, and the DRDA) to verify the effectiveness in the cross-subject environment on dataset 2a of BCI competition IV. When our proposed module was attached to each conventional DA method, the average accuracy was improved by much as 4.67 %, 0.76 %, and 1.72 %, respectively. Hence, we demonstrated that our proposed module could emphasize the information related to MI characteristics. The code of our implementation is accessible on GitHub.[1].},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
*Imagination/physiology
Movement/physiology
Signal Processing, Computer-Assisted
Algorithms

@article {pmid40039926,
year = {2024},
author = {Zhong, Y and Yao, L and Wang, Y},
title = {Enhanced BCI Performance using Diffusion Model for EEG Generation.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782900},
pmid = {40039926},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Electroencephalography/methods ; Algorithms ; Signal Processing, Computer-Assisted ; Imagination/physiology ; },
abstract = {In the realm of Motor Imagery (MI)-based Brain-Computer Interface (BCI), the widespread adoption of deep learning-based algorithms has resulted in an increased demand for a larger training sample size, thereby placing a heightened burden on users. This study advocates the utilization of one of the most advanced generative models, the denoising diffusion probabilistic model (DDPM), for the artificial synthesis of Electroencephalogram (EEG) raw signals. The quality of the generated EEG signals is evaluated through both qualitative and quantitative analyses. Through dimensionality reduction projection, we observed a notable similarity in the data distributions between the generated EEG signals and real EEG signals. Additionally, spectral analysis indicates a striking similarity in energy distribution between the two, accompanied by the presence of an event-related synchronization (ERS) phenomenon in the generated EEG signals. Quantitative analysis reveals that the accuracy of generated EEG signals for left and right-hand motor imagery tasks is 89.81 ± 2.11%, with discriminative information related to classes predominantly concentrated in the motor-sensory cortex area and alpha-beta frequency band. Furthermore, the integration of generated EEG samples contributes to a 3.17% improvement in the classification performance of BCI-deficiency subjects. These artificially generated EEG signals exhibit promising potential for application in calibrating MI-BCI deep learning models, thereby alleviating the burden on participants.},
}

*Brain-Computer Interfaces
Humans
*Electroencephalography/methods
Algorithms
Signal Processing, Computer-Assisted
Imagination/physiology

@article {pmid40039924,
year = {2024},
author = {Hoshino, T and Kanoga, S and Aoyama, A},
title = {Channel- and Label-Flip Data Augmentation for Motor Imagery-Based Brain-Computer Interfaces.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782028},
pmid = {40039924},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Imagination/physiology ; Signal Processing, Computer-Assisted ; Machine Learning ; Movement/physiology ; Algorithms ; Brain/physiology ; },
abstract = {Achieving high classification accuracy in motor-imagery-based brain-computer interfaces (BCIs) requires substantial amounts of training data. A challenge arises because of the impracticality of measuring large amounts of data from users. Data augmentation (DA) has emerged as a promising solution for this challenge. We propose a novel DA method called channel&label-flip DA that involves not only flipping channels but also flipping class labels. This method is based on the neuroscience finding that motor imageries of left- and right-hand movements are roughly symmetrical. The efficiency of the proposed method was evaluated using the OpenBMI dataset, which comprises electroencephalograms collected from 54 participants engaged in left- and right-hand motor imagery tasks. To compare the impact on classifiers, we employed three classical machine learning models utilizing filter bank common spatial pattern features, along with a deep learning-based model that uses raw signal input. As a result, the channel&label-flip DA improved the classification accuracy on average, whereas simple flipping of the channels reduced the classification accuracy compared to the case without DA.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Imagination/physiology
Signal Processing, Computer-Assisted
Machine Learning
Movement/physiology
Algorithms
Brain/physiology

@article {pmid40039912,
year = {2024},
author = {Tan, J and Wang, Y},
title = {Dynamic Inverse Reinforcement Learning for Feedback-driven Reward Estimation in Brain Machine Interface Tasks.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782800},
pmid = {40039912},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Reward ; *Algorithms ; Reinforcement, Psychology ; Machine Learning ; Feedback ; },
abstract = {Reinforcement learning (RL)-based brain machine interfaces (BMIs) provide a promising solution for paralyzed people. Enhancing the decoding performance of RL-based BMIs relies on the design of effective reward signals. Inverse reinforcement learning (IRL) offers an approach to infer subjects' own evaluation from the observed behavior. However, applying IRL to extract reward information in complex BMI tasks requires consideration of the dynamics of subjects' goal during the control process. This dynamic nature of subjects' evaluation requires the IRL method to be able to estimate a time varying reward function. Previous IRL methods applied in BMI systems only estimated a static reward function. Existing IRL algorithms for dynamic reward estimation employ optimization methods to approximate the reward map for each state at each time, which demands substantial amounts of data to achieve convergence. In this paper, we propose a dynamic IRL method to estimate the feedback-driven reward of subjects during BMI tasks. We utilize a state-observation model to continuously infer the reward value for each state, with sensory feedback serving as the external input to model the transition process of the reward. We evaluate our proposed method on a simulated BMI fetch task, which is a multistep task with a time varying reward function. Our method demonstrates improved reward estimation close to the ground truth value, and it significantly outperforms the existing dynamic IRL method when the map size exceeds 25(p<0.01). These preliminary results suggests that the dynamic IRL method for feedback-driven reward estimation holds potential for improving the design of RL-based BMIs.},
}

*Brain-Computer Interfaces
Humans
*Reward
*Algorithms
Reinforcement, Psychology
Machine Learning
Feedback

@article {pmid40039908,
year = {2024},
author = {Patel, K and Safavi, F and Chandramouli, R and Vinjamuri, R},
title = {Transformer-Based Emotion Recognition with EEG.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781700},
pmid = {40039908},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Emotions/physiology ; *Signal Processing, Computer-Assisted ; Brain-Computer Interfaces ; Male ; Female ; Brain/physiology ; },
abstract = {Emotion recognition via electroencephalography (EEG) has emerged as a pivotal domain in biomedical signal processing, offering valuable insights into affective states. This paper presents a novel approach utilizing a tailored Transformer-based model to predict valence and arousal levels from EEG signals. Diverging from traditional Transformers handling singular sequential data, our model adeptly accommodates multiple EEG channels concurrently, enhancing its ability to discern intricate temporal patterns across the brain. The modified Transformer architecture enables comprehensive exploration of spatiotemporal dynamics linked with emotional states. Demonstrating robust performance, the model achieves mean accuracies of 92.66% for valence and 91.17% for arousal prediction, validated through 10-fold cross-validation across subjects on the DEAP dataset. Trained for subject-specific analysis, our methodology offers promising avenues for enhancing understanding and applications in emotion recognition through EEG. This research contributes to a broader discourse in biomedical signal processing, paving the way for refined methodologies in decoding neural correlates of emotions with implications across various domains including brain-computer interfaces, and human-robot interaction.},
}

Humans
*Electroencephalography/methods
*Emotions/physiology
*Signal Processing, Computer-Assisted
Brain-Computer Interfaces
Male
Female
Brain/physiology

@article {pmid40039888,
year = {2024},
author = {Sturgill, BS and Jiang, MS and Jeakle, EN and Smith, TJ and Hoeferlin, GF and Duncan, J and Thai, TTD and Hess, JL and Alam, NN and Hernandez-Reynoso, AG and Capadona, JR and Pancrazio, JJ},
title = {Antioxidant Coated Microelectrode Arrays: Effects on Putative Inhibitory and Excitatory Neurons.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10781940},
pmid = {40039888},
issn = {2694-0604},
mesh = {*Microelectrodes ; *Neurons/physiology ; Animals ; *Antioxidants/pharmacology ; Metalloporphyrins/pharmacology ; Rats ; Coated Materials, Biocompatible/chemistry ; Brain-Computer Interfaces ; },
abstract = {Intracortical microelectrode arrays (MEAs) are used to record neural activity in vivo at single-cell resolution for both neuroscience studies and for engineering restorative devices such as brain-computer interfaces (BCIs). The recording performance of these devices are known to degrade over weeks to months after implantation due, in part, to neuroinflammation and oxidative stress. Characterizing and mitigating the degradation of recording performance is of particular interest for chronic applications. Literature suggests that inhibitory neurons may be more susceptible to oxidative stress than excitatory neurons. In this study, we classify recorded neural signals as either putative inhibitory or excitatory based on their waveform characteristics and aim to identify if one preferentially benefits from the use of a Mn(III)tetrakis94-benzoic acid)porphyrin (MnTBAP) coating to reduce reactive oxygen species, which we have previously demonstrated improves chronic neural recordings. In this study, we found that the MnTBAP coating affects these two classes of neurons differently, depending on the cortical depth. The MnTBAP coating improves the number of putative inhibitory signals recorded on the middle electrode sites (L5) and putative excitatory units on the superficial (L2/3 & L4) electrode sites. Our results suggest that decreases in recording performance may be influenced by both cortical depth and neuronal cell type. Furthermore, we show that the benefits of a MnTBAP coating to chronic neural recordings differ between putative inhibitory and excitatory neurons with a depth dependence.},
}

*Microelectrodes
*Neurons/physiology
Animals
*Antioxidants/pharmacology
Metalloporphyrins/pharmacology
Rats
Coated Materials, Biocompatible/chemistry
Brain-Computer Interfaces

@article {pmid40039787,
year = {2024},
author = {Won, E and Lim, S and Kim, Y and Dong, SY},
title = {Toward the TCN-based Real-Time BCI System for Target Detection.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782928},
pmid = {40039787},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Electroencephalography/methods ; Signal Processing, Computer-Assisted ; Deep Learning ; Male ; Adult ; Neural Networks, Computer ; },
abstract = {This study focuses on developing a real-time Brain-Computer Interface (BCI) system, specifically designed for military applications, to enhance target detection in rapid serial visual presentation (RSVP) tasks. The proposed BCI system utilizes electroencephalogram (EEG) signals based on dry electrodes, known for their exceptional temporal resolution, to identify swiftly specific target symbols within sequences of visual stimuli. Leveraging deep learning techniques, particularly Temporal Convolutional Networks (TCN), this study demonstrates the accuracy and efficiency improvement in target detection for RSVP tasks. According to our findings, the adaptability and efficacy of TCN in handling temporal dynamics of EEG signals exhibit outstanding performance in target detection, thus offering the potential for accurate and efficient real-time BCI system.},
}

*Brain-Computer Interfaces
Humans
*Electroencephalography/methods
Signal Processing, Computer-Assisted
Deep Learning
Male
Adult
Neural Networks, Computer

@article {pmid40039782,
year = {2024},
author = {Park, JH and Lee, SH and Lee, SW},
title = {Towards EEG-based Talking-face Generation for Brain Signal-driven Dynamic Communication.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10781922},
pmid = {40039782},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Brain/physiology/diagnostic imaging ; Signal Processing, Computer-Assisted ; Brain-Computer Interfaces ; Face/physiology ; Speech/physiology ; Communication ; },
abstract = {Research on decoding speech or generating images from human brain activity holds intriguing potential as neuroprosthesis for patients and innovative communication tools for general users. However, previous studies have been constrained in generating fragmented or abstract outputs, rendering them less applicable for serving as an alternative form of communication. In this paper, we propose an integrated framework that synthesizes speech from non-invasive speech-related brain signals and generates a talking-face that performs "lip-sync" using intermediate input decoded from brain signals. For realistic and dynamic brain signal-mediated communication, we generated a personalized talking-face by utilizing various forms of target data such as a real face or an avatar. Additionally, we performed a denoising process to enhance the quality of synthesized voices from brain signals, and to minimize unnecessary facial movements according to the noise. Therefore, clear and natural talking-faces, applicable to both real faces and avatars, could be generated from noisy brain signals, enabling dynamic communication. These findings serve as a pivotal contribution to the advancement of brain signal-driven face-to-face communication through the provision of integrated speech and visual interfaces. This represents a significant step towards the development of a more intuitive and dynamic brain-computer interface communication system.},
}

Humans
*Electroencephalography/methods
*Brain/physiology/diagnostic imaging
Signal Processing, Computer-Assisted
Brain-Computer Interfaces
Face/physiology
Speech/physiology
Communication

@article {pmid40039768,
year = {2024},
author = {He, F and Zhang, S and Yang, M and Meng, J and Xu, M and Meng, L and Ming, D},
title = {Prediction errors from distinct perspectives induce separable EEG features for brain-computer interface.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781933},
pmid = {40039768},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Male ; *Algorithms ; Female ; Adult ; Young Adult ; Evoked Potentials/physiology ; },
abstract = {The ability to efficiently detect error is fundamental for human adaptive behaviors, and plays an increasingly crucial role in developing more intelligent brain-computer interface (BCI). Error-related potential (ErrP), which can reflect prediction error, has been widely used by the BCI to read whether outcomes accord with users' expectation or not. However, current ErrP-BCI cannot distinguish the prediction error is induced by user's own (first-person perspective, 1PP) or other's (third-person perspective, 3PP) wrong action, hindering it from being applied in social interactions. This study used virtual reality (VR) to make subjects aware of prediction errors from the first- or third-person perspective, and recorded electroencephalogram (EEG) data of 22 healthy subjects. Event-related potential (ERP), event-related spectral perturbation (ERSP), inter-trial coherence (ITC) and shrinkage discriminant canonical pattern matching (SKDCPM) algorithm were used to investigate EEG features and the separability of prediction errors induced by distinct perspectives. Consequently, ErrP induced by the 1PP emerged significantly earlier than that of 3PP, and caused greater ERSP and ITC in the prefrontal region in the theta and alpha bands. Decoding result achieved 76.4%± 9.13% accuracy for the two types of errors (1PP-incorrect vs 3PP-incorrect). This study fills in the fine-grained classification of different error types and provides a finer metric for the systematic error correction efficiency of two-person collaborative brain control, which is the basis for future human-machine hybrid intelligence.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Male
*Algorithms
Female
Adult
Young Adult
Evoked Potentials/physiology

@article {pmid40039762,
year = {2024},
author = {Li, M and Wang, M and Wang, Y},
title = {An Adaptive Superposition Point Process Model with Neuronal Encoding Engagement Identification.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781885},
pmid = {40039762},
issn = {2694-0604},
mesh = {*Neurons/physiology ; *Brain-Computer Interfaces ; *Models, Neurological ; Animals ; Humans ; Algorithms ; },
abstract = {Neuronal encoding is realized by modulating firing rates in response to various encoding factors, including external stimuli, behaviors, and complex neural interactions. The neuronal encoding engagement of various factors are dynamic, which reflects how neurons aggregate different information. The process of uncovering the extent to which these factors contribute to neuronal encoding over time is neuronal encoding engagement identification. Brain-machine interface (BMI) establishes a closed-loop framework to investigate how neurons response to different encoding factors. Since neurons don't fully participate in encoding one specific factor, accurate encoding engagement identification contributes to leveraging encoding and decoding in more naturalistic BMI application scenarios. However, previous works focus on modeling and estimating tuning properties instead of analyzing the neuronal information aggregation. We develop a dual adaptive superposition point process filter (DASPPF), which explicitly incorporates various encoding factors. DASPPF not only enables decoding kinematics but also identifies the engagement of individual kinematics encoding and functional neural connectivity encoding. DASPPF is validated on numerical simulations of monkey circle-tracking tasks. The proposed method can effectively promote decoding performance and uncover how neurons engage themselves in different effects with point process observation, which may help enhance the development of neurotechnologies.},
}

*Neurons/physiology
*Brain-Computer Interfaces
*Models, Neurological
Animals
Humans
Algorithms

@article {pmid40039684,
year = {2024},
author = {Tang, Y and Robinson, N and Fu, X and Thomas, KP and Wai, AAP and Guan, C},
title = {Reconstruction of Continuous Hand Grasp Movement from EEG Using Deep Learning.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781850},
pmid = {40039684},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Deep Learning ; *Movement/physiology ; *Hand Strength/physiology ; Adult ; *Brain-Computer Interfaces ; Male ; Female ; Hand/physiology ; Young Adult ; Signal Processing, Computer-Assisted ; Algorithms ; Neural Networks, Computer ; },
abstract = {Brain-Computer Interface (BCI) is a promising neu-rotechnology offering non-muscular control of external devices, such as neuroprostheses and robotic exoskeletons. A new yet under-explored BCI control paradigm is Motion Trajectory Prediction (MTP). While MTP provides continuous control signals suitable for high-precision tasks, its feasibility and applications are challenged by the low signal-to-noise ratio, especially in noninvasive settings. Previous research has predominantly focused on kinematic reconstruction of upper (e.g., arm reaching) and lower limbs (e.g., gait). However, finger movements have received much less attention, despite their crucial role in daily activities. To address this gap, our study explores the potential of noninvasive Electroencephalography (EEG) for reconstructing finger movements, specifically during hand grasping actions. A new experimental paradigm to collect multichannel EEG data from 20 healthy subjects, while performing full, natural hand opening and closing movements, was designed. Employing state-of-the-art deep learning algorithms, continuous decoding models were constructed for eight key finger joints. The Convolutional Neural Network with Attention approach achieved an average decoding performance of r=0.63. Furthermore, a post-hoc metric was proposed for hand grasp cycle detection, and 83.5% of hand grasps were successfully detected from the reconstructed motion signals, which can potentially serve as a new BCI command. Explainable AI algorithm was also applied to analyze the topographical relevance of trained features. Our findings demonstrate the feasibility of using EEG to reconstruct hand joint movements and highlight the potential of MTP-BCI in control and rehabilitation applications.},
}

Humans
*Electroencephalography/methods
*Deep Learning
*Movement/physiology
*Hand Strength/physiology
Adult
*Brain-Computer Interfaces
Male
Female
Hand/physiology
Young Adult
Signal Processing, Computer-Assisted
Algorithms
Neural Networks, Computer

@article {pmid40039675,
year = {2024},
author = {Tang, C and Jiang, D and Chen, B},
title = {MEG Channel Selection Using Copula Entropy-Based Transfer Entropy for Motor Imagery BCI.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782066},
pmid = {40039675},
issn = {2694-0604},
mesh = {*Magnetoencephalography/methods ; Humans ; *Brain-Computer Interfaces ; *Entropy ; Imagination/physiology ; Algorithms ; Movement/physiology ; },
abstract = {Multi-channel magnetoencephalography (MEG) data provides high spatiotemporal resolution for motor imagery (MI)-based brain-machine interfaces (BCIs). However, not all channels contribute to the performance of BCIs. Taking into account the importance of specific channels in measuring their causal relationships with other channels during MI tasks, a novel channel selection method using copula entropy-based transfer entropy (CTE) is proposed to select task-relevant channels. Experiments on a publicly available dataset validate the effectiveness of the proposed methods. Compared to using all channels, channel selection based on CTE can significantly (p < 0.05) improve single-session classification accuracy and greatly reduce the number of MEG channels. Cross-session classification also outperforms the competing method.},
}

*Magnetoencephalography/methods
Humans
*Brain-Computer Interfaces
*Entropy
Imagination/physiology
Algorithms
Movement/physiology

@article {pmid40039672,
year = {2024},
author = {Irvine, B and Abou-Zeid, H and Kirton, A and Kinney-Lang, E},
title = {Benchmarking motor imagery algorithms for pediatric users of brain-computer interfaces.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782164},
pmid = {40039672},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; Child ; Adolescent ; *Algorithms ; Child, Preschool ; Male ; Benchmarking ; Female ; Electroencephalography/methods ; Imagination/physiology ; },
abstract = {Brain-computer interfaces (BCIs) can enable opportunities for self-expression and life participation for children with severe neurological disabilities. Unfortunately, the development and evaluation of state-of-the-art algorithms has largely neglected pediatric users. This work tests 12 state-of-the-art algorithms for motor imagery classification on three datasets of typically developing pediatric users (n=94 ages 5-17). When all datasets were combined, there were no significant differences between most non-deep learning algorithms, with all having a mean AUC score of 0.64 or 0.65. All the non-deep learning algorithms significantly outperformed the deep learning algorithms, which can be partially attributed to a lack of hyperparameter tuning. The best of the deep learning algorithms was ShallowConvNet, with a mean AUC score of 0.57. Of the algorithms tested, only the filter bank common spatial pattern (FBCSP) and ShallowConvNet exhibited significant age effects. This general lack of age effects, combined with examples of children as young as 6 having AUC scores as high as 0.8, provides evidence that young children are capable of producing measurable motor imagery activations. The age effects that were present for some algorithms suggest that the changing EEG patterns associated with development could have a measurable impact on classification algorithm outcomes, and such algorithms should be evaluated to ensure that they are not performing disproportionately poorly for younger children. This work serves as a first step towards ensuring that the state-of-the-art improvements in BCI classification can be evaluated, and where necessary, adapted to meet the needs of pediatric users.},
}

Humans
*Brain-Computer Interfaces
Child
Adolescent
*Algorithms
Child, Preschool
Male
Benchmarking
Female
Electroencephalography/methods
Imagination/physiology

@article {pmid40039651,
year = {2024},
author = {Kolbl, N and Tziridis, K and Krauss, P and Schilling, A},
title = {Methodological Considerations in the Analysis of Acoustically Evoked Neural Signals: A Comparative Study of Active EEG, Passive EEG and MEG.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-7},
doi = {10.1109/EMBC53108.2024.10782081},
pmid = {40039651},
issn = {2694-0604},
mesh = {Humans ; *Magnetoencephalography/methods ; *Electroencephalography/methods ; Evoked Potentials, Auditory/physiology ; Adult ; Male ; Female ; Brain-Computer Interfaces ; Acoustic Stimulation ; Brain/physiology ; },
abstract = {Analyzing and deciphering brain signals on a single trial base is the main goal of brain-computer interface (BCI) research as well as neurolinguistics. In the present study, we have evaluated the efficacy of three neuroimaging techniques-active electroencephalography (EEG), passive EEG, and magnetoencephalography (MEG)-in capturing and evaluating brain activity in response to auditory stimuli. The main goals of our research included two primary components: first, to identify ROIs, and second, to determine the appropriate number of stimulus samples needed to achieve a meaningful level of reliability. To estimate this number of measurement repetitions we performed step-wise sub-sampling combined with permutation testing. This involved a detailed comparison of event-related potentials resp. fields (ERPs, ERFs) elicited by auditory stimuli such as acoustic clicks and continuous speech. Our results show that active EEG outperformed passive EEG and MEG in sensor space. However, MEG demonstrated superior signal localization in source space. These results also highlight the complexity of developing real-time speech BCIs.},
}

Humans
*Magnetoencephalography/methods
*Electroencephalography/methods
Evoked Potentials, Auditory/physiology
Adult
Male
Female
Brain-Computer Interfaces
Acoustic Stimulation
Brain/physiology

@article {pmid40039633,
year = {2024},
author = {Lu, JB and Tsao, Y and Wang, YT},
title = {Design and Evaluate Semi-dry Watermill-like EEG Electrodes.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782960},
pmid = {40039633},
issn = {2694-0604},
mesh = {*Electroencephalography/instrumentation/methods ; *Electrodes ; Humans ; *Equipment Design ; Brain-Computer Interfaces ; },
abstract = {Semi-dry electrodes act as the middle ground between wet and dry electrodes as they not only have similar contact features (equivalent circuit) with Ag/AgCl-based wet electrodes but also carry the conduct material in their cavity or sponge (e.g. absorb saline water) for long-term brain-computer interface(BCI) applications. However, the trade off between hair-layer penetration and dose control of conductive material is challenging e.g. two electrodes might be bridged when the headset continuously presses or squeezes the reservoir and electrolyte flows on the scalp. The goal of this study is to design, prototype, and evaluate watermill-like electroencephalogram (EEG) electrodes that aim to simultaneously overcome two issues: hair-layer penetration and dose control of conductive material. Two electrode profiles, straight and spiral, were 3D printed, coated and evaluated with participants' EEGs. Without any help from skilled technicians, the self-wearing mechanical design allows users to wear and acquire their EEGs in few minutes. In addition, the refillable reservoir enable the possibility for long-term BCI applications. The results show that the proposed electrodes can read neural activities on the hair-covered area. Furthermore, straight profile electrodes outperform the spiral profile in the steady-state visually evoked potential (SSVEP) response. In sum, the watermill-like EEG electrodes can shorten the preparation time as well as the dose control of conductive material for naive users. The results suggest the proposed electrodes might open opportunities for BCI users to develop real-world BCI applications in the future.},
}

*Electroencephalography/instrumentation/methods
*Electrodes
Humans
*Equipment Design
Brain-Computer Interfaces

@article {pmid40039626,
year = {2024},
author = {Lin, X and Eldele, E and Chen, Z and Wu, M and Ng, HW and Guan, C},
title = {Bi-hemisphere Interaction Convolutional Neural Network for Motor Imagery Classification.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782755},
pmid = {40039626},
issn = {2694-0604},
mesh = {Humans ; *Neural Networks, Computer ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Imagination/physiology ; Brain/physiology ; Signal Processing, Computer-Assisted ; },
abstract = {Decoding EEG-based, Motor Imagery Brain-Computer Interfaces (MI-BCI) in a subject-independent manner is very challenging due to high dimensionality of the EEG signal, and high inter-subject variability. In recent years, Convolutional neural networks (CNNs) have significantly enhanced decoding accuracy. Nevertheless, the majority of these CNN designs did not explicitly incorporate the inter-hemisphere functional connections, omitting crucial spatial information. Notably, in binary MI decoding of the left-hand versus right-hand, the Event-Related Desynchronization is observed in the contralateral hemisphere. Building upon this concept and various Neuroscience research, we have designed a CNN architecture that forges a functional connection between the two hemispheres. Specifically, we applied the Channel Average Referencing to one hemisphere and compared the output with all channels of the opposite hemisphere. Then, we utilized the cosine similarity to identify the most correlated channels and combined with them the original hemisphere for spatial filtering to learn the inter-hemispheric connections. This innovative technique aligns more closely with the actual brain functionality. Our method has demonstrated superior results on the Cho2017 and OpenBMI datasets, underscoring its effectiveness.},
}

Humans
*Neural Networks, Computer
*Brain-Computer Interfaces
*Electroencephalography/methods
Imagination/physiology
Brain/physiology
Signal Processing, Computer-Assisted

@article {pmid40039616,
year = {2024},
author = {Guerrero-Mendez, CD and Rivera-Flor, H and Villa-Parra, AC and Bastos-Filho, TF},
title = {Exploring Novel Practical Approach to Post-Stroke Upper-Limb Neurorehabilitation Based on Complex Motor Imagery Tasks.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-6},
doi = {10.1109/EMBC53108.2024.10782286},
pmid = {40039616},
issn = {2694-0604},
mesh = {Humans ; *Stroke Rehabilitation/methods ; *Upper Extremity/physiopathology ; Male ; Electroencephalography/methods ; Female ; Stroke/physiopathology/complications ; Imagery, Psychotherapy/methods ; Imagination/physiology ; Middle Aged ; Neurological Rehabilitation/methods ; Adult ; },
abstract = {Motor imagery (MI) is one of the main strategies for upper-limb movement rehabilitation in post-stroke individuals. Promising results of MI applied for rehabilitation have been reported in the literature. However, there is currently a need related to the recovery of movements aimed to Activities of Daily Living (ADLs) for individuals with severe motor impairments. Therefore, this study presents the evaluation of a novel MI protocol for post-stroke upper-limb neurorehabilitation using complex tasks related to the manipulation of a drinking cup. The protocol is based on the Action Observation (AO), which was used under a first-person 2D virtual reality. Subjects had to simultaneously imagine the movements presented in AO for the manipulation of a cup varying in four positions. EEG signals were recorded from 16 channels located mainly in the motor cortex of the brain. Two computational strategies based on Riemannian Geometry (RG) with and without Feature Selection (FS) using Pair-Wise Feature Proximity (PWFP) were implemented for the binary identification of each complex MI-Task vs. MI-Rest. This approach was evaluated on 30 healthy individuals and 2 post-stroke individuals. Using Linear Discriminant Analysis (LDA) as a classifier, the results report a maximum accuracy of 0.78 for both healthy and post-stroke individuals, and a minimum FPR of 0.21 and 0.13 for healthy and post-stroke individuals, respectively. This highlights the potential use of this type of paradigms for the implementation of more robust BCI systems that allow the rehabilitation of movements close to ADLs. Therefore, complex MI tasks may be a suitable variant for rehabilitation in post-stroke individuals.},
}

Humans
*Stroke Rehabilitation/methods
*Upper Extremity/physiopathology
Male
Electroencephalography/methods
Female
Stroke/physiopathology/complications
Imagery, Psychotherapy/methods
Imagination/physiology
Middle Aged
Neurological Rehabilitation/methods
Adult

@article {pmid40039598,
year = {2024},
author = {Noble, SC and Ward, T and Ringwood, JV},
title = {Assessing the Impact of Environment and Electrode Configuration on P300 Speller Performance and EEG Signal Quality.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782158},
pmid = {40039598},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/instrumentation ; *Electrodes ; Adult ; *Brain-Computer Interfaces ; Male ; Female ; *Event-Related Potentials, P300/physiology ; Signal Processing, Computer-Assisted ; Young Adult ; Environment ; },
abstract = {Recent years have seen extensive use of brain-computer interfaces (BCIs) using electroencephalography (EEG). A critical element in BCI research is electrode selection, which influences performance, experiment duration, resource utilization, and consequently, cost. Electrode choice is partly dictated by the study location, as environmental electrical noise can impact EEG signal quality. This study evaluates the performance of a P300 speller and EEG signal quality using 4-, 6-, 8-, and 16-electrode configurations in two different office environments. Ten healthy adults participated in a single session, using a P300 speller to spell three words with each electrode set. Participants were split between two locations, with five individuals in each. Significant performance disparities were observed between the locations. Notably, within each location, the performance differences among 4-, 6-, and 8-electrode sets were minimal; only the 16-electrode set outperformed the others in both settings. The location associated with poorer performances also exhibited lower P300 amplitudes and higher levels of mains electricity noise.},
}

Humans
*Electroencephalography/instrumentation
*Electrodes
Adult
*Brain-Computer Interfaces
Male
Female
*Event-Related Potentials, P300/physiology
Signal Processing, Computer-Assisted
Young Adult
Environment

@article {pmid40039596,
year = {2024},
author = {Ben Ticha, MB and Ran, X and Roussel, P and Bocquelet, F and Le Godais, G and Aubert, M and Costecalde, T and Struber, L and Zhang, S and Charvet, G and Kahane, P and Chabardes, S and Yvert, B},
title = {A Vision Transformer Architecture For Overt Speech Decoding From ECoG Data.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781877},
pmid = {40039596},
issn = {2694-0604},
mesh = {Humans ; *Speech/physiology ; *Brain-Computer Interfaces ; *Neural Networks, Computer ; Algorithms ; Electrocorticography/methods ; },
abstract = {Speech Brain-Computer Interfaces rely on decoding algorithms that transform neural activity into speech. A current challenge is to achieve intelligible speech synthesis in real time from continuous ongoing brain activity, ideally without the need of language models that prevent free-speech production. As a first step toward this goal, we introduce here an encoder-decoder architecture, in which neural data is first encoded into a latent space using a multi-layer vision transformer (ViT), and then these latent variables are converted into acoustic coefficients using a bidirectional LSTM recurrent network. This network is compared to a more conventional architecture where the encoding is performed using a convolutional neural network. Moreover, we introduce a new data-driven data augmentation strategy based on Dynamic Time Warping (DTW) to increase a training dataset based on the intrinsic variability of its input neural features. On two ECoG datasets obtained in participants performing an overt speech task, we found that ViT-encoding outperforms CNN-encoding to predict produced speech offline and that DTW-based data augmentation also improves decoding performance.},
}

Humans
*Speech/physiology
*Brain-Computer Interfaces
*Neural Networks, Computer
Algorithms
Electrocorticography/methods

@article {pmid40039592,
year = {2024},
author = {Schrag, E and Comaduran-Marquez, D and Kirton, A and Kinney-Lang, E},
title = {Textured Stimuli Comfort and Response in SSVEP-Based Brain Computer Interface.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782587},
pmid = {40039592},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; Adult ; *Evoked Potentials, Visual/physiology ; Male ; Female ; Young Adult ; Photic Stimulation ; Signal-To-Noise Ratio ; Electroencephalography/methods ; },
abstract = {State of the art steady-state visual evoked potential (SSVEP) brain computer interface (BCI) stimuli are commonly high-contrast, solid color flashing objects which can contribute to visual discomfort and fatigue. The use of low-contrast, textured flashing stimuli is proposed as a more comfortable alternative stimulus presentation paradigm. Eight participants (aged 19-35) were presented with four textured stimuli at varying frequencies, alongside standard stimuli. Results indicate significant effects of stimulus type as well as an interaction between frequency and channel subset on signal-to-noise ratio (SNR) values. Comfort scores consistently favored textured stimuli over high-contrast options at all frequencies The observed lack of SNR differences between stimulus conditions supports the feasibility of using textured stimuli in BCIs. This study lays a foundation for developing comfortable and effective BCI systems. The promising results of textured stimuli suggest a potential alternative for SSEVP-based BCI systems, emphasizing the importance of balancing neural responses and user comfort in stimulus design.},
}

Humans
*Brain-Computer Interfaces
Adult
*Evoked Potentials, Visual/physiology
Male
Female
Young Adult
Photic Stimulation
Signal-To-Noise Ratio
Electroencephalography/methods

@article {pmid40039576,
year = {2024},
author = {Jiang, R and Qiu, S and Wang, Y and Zhang, C and He, H},
title = {Evaluation of EEG and MEG responses during Fine Motor Imagery from the same limb.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782038},
pmid = {40039576},
issn = {2694-0604},
mesh = {Humans ; *Magnetoencephalography/methods ; *Electroencephalography/methods ; Male ; *Brain-Computer Interfaces ; Adult ; *Imagination/physiology ; Female ; Movement/physiology ; },
abstract = {Motor imagery (MI) is an important brain-computer interface (BCI) paradigm. BCI systems based on fine MI can provide an intuitive control pathway of the outer device. Electroencephalography (EEG) is a widely used modality for MI due to its high temporal resolution and portability. Magnetoencephalography (MEG) has high spatial and temporal resolution, which has received more and more attention. This study designed four kinds of MI tasks of different joints from the same upper limb, including finger, wrist, elbow, and shoulder joints, and additionally added a resting task. The EEG and MEG signals of eight subjects were acquired synchronously. Analysis was conducted on the EEG and MEG data to find the time, time-frequency, and spatial difference between MI tasks of different joints from the same limb. The induced event-related desynchronization (ERD) in EEG signals at the electrode position of the left motor area are more broad and stronger in the alpha frequency band than that in MEG signals during fine MI tasks. From the topographical distribution, different MI tasks affects the area and intensity of the activated area, and topographical distribution of MEG signals in different MI tasks are more discriminative than that of EEG signals. Moreover, the analysis of movement-related cortical potentials (MRCP) showed that significant negative potentials were detected near the onset of the motor imagery events and there is a significant difference in temporal dimension between magnetoencephalogram and electroencephalogram signals. The work implies that there exist the separable differences between EEG and MEG during fine MI tasks, which can be utilized to build a multimodal classification method for fine MI-BCI systems.},
}

Humans
*Magnetoencephalography/methods
*Electroencephalography/methods
Male
*Brain-Computer Interfaces
Adult
*Imagination/physiology
Female
Movement/physiology

@article {pmid40039573,
year = {2024},
author = {Delavari, F and Santaniello, S},
title = {Role of Scalp EEG Brain Connectivity in Motor Imagery Decoding for BCI Applications.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781532},
pmid = {40039573},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Electroencephalography/methods ; *Brain/physiology/diagnostic imaging ; Scalp/physiology ; Imagination/physiology ; },
abstract = {Brain Connectivity (BC) features of multichannel EEG have been proposed for Motor Imagery (MI) decoding in Brain-Computer Interface applications, but the advantages of BC features vs. single-channel features are unclear. Here, we consider three BC features, i.e., Phase Locking Value (PLV), Granger Causality, and weighted Phase Lag Index, and investigate the relationship between the most central nodes in BC-based networks and the most influential EEG channels in single-channel classification based on common spatial pattern filtering. Then, we compare the accuracy of MI decoders that use BC features in source vs. sensor space. Applied to the BCI Competition VI Dataset 2a (left- vs. right-hand MI decoding), our study found that PLV in sensor space achieves the highest classification accuracy among BC features and has similar performance compared to single-channel features, while the transition from sensor to source space reduces the average accuracy of BC features. Across all BC measures, the network topology is similar in left- vs. right-hand MI tasks, and the most central nodes in BC-based networks partially overlap with the most influential channels in single-channel classification.},
}

*Brain-Computer Interfaces
Humans
*Electroencephalography/methods
*Brain/physiology/diagnostic imaging
Scalp/physiology
Imagination/physiology

@article {pmid40039515,
year = {2024},
author = {Marquez, DC and Minhas, A and Kinney-Lang, E and Kirton, A},
title = {Automated Hyper-Parameter Optimization for Eye Movement Artifact Removal.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782395},
pmid = {40039515},
issn = {2694-0604},
mesh = {Humans ; *Artifacts ; *Electroencephalography/methods ; *Eye Movements/physiology ; *Brain-Computer Interfaces ; Algorithms ; Signal Processing, Computer-Assisted ; },
abstract = {Brain-computer interface (BCI) systems allow users to control external devices with their brain waves. However, electroencephalography (EEG) signals used by most BCI systems are prone to artifacts from various sources (e.g., muscle activity, eye movements, and electrical interference). These artifacts can degrade the performance and usability of BCI systems. Many tools exist to eliminate these artifacts. However, not all methods are automated, and some might require tuning certain hyper-parameters for optimal performance. We propose a method to automatically optimize the hyper-parameters of an eye blink artifact removal tool to improve the removal of artifacts in resting state EEG. We use a subset of eye movement artifacts to optimize the hyper-parameters using the EEG Quality Index (EQI) as the objective function. The optimized hyper-parameters are then used in a test artifact to quantify the improvement of the EQI. Results show improvement in the EQI when compared to the default artifact removal hyper-parameters, and raw EEG traces. We conclude that our method can provide a personalized and robust artifact removal solution for BCI users with complex needs.},
}

Humans
*Artifacts
*Electroencephalography/methods
*Eye Movements/physiology
*Brain-Computer Interfaces
Algorithms
Signal Processing, Computer-Assisted

@article {pmid40039504,
year = {2024},
author = {Osborn, LE and Christie, B and McMullen, DP and Thomas, TM and Thompson, MC and Nickl, RW and Pawar, AS and Wester, BA and Cantarero, GL and Celnik, PA and Crone, NE and Fifer, MS and Tenore, FV},
title = {Artificial touch feedback using microstimulation of human somatosensory cortex to convey grip force from a robotic hand.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782061},
pmid = {40039504},
issn = {2694-0604},
mesh = {Humans ; *Somatosensory Cortex/physiology/physiopathology ; *Robotics/instrumentation ; *Hand Strength/physiology ; *Hand/physiology ; *Touch/physiology ; Brain-Computer Interfaces ; Male ; Electric Stimulation ; Feedback, Sensory/physiology ; },
abstract = {Invasive brain-machine interfaces can help restore function through the control of external devices while the addition of intracortical microstimulation (ICMS) can elicit sensations of touch and help provide further benefits for individuals living with sensorimotor deficits. However, the extent of tactile information that can be conveyed through ICMS has not been fully explored. In a human participant with spinal cord injury and chronically implanted microelectrode arrays, we used ICMS to the somatosensory cortex to provide grip force feedback in the hands during grasping of objects with varying stiffness with a robotic arm. Using only ICMS-evoked touch sensations, the participant was able to identify between two and three objects with an accuracy of 92% and 67%, respectively. In a compliant grasping task with the goal of grasping a delicate object without crushing it, objects were deformed on average only 2.8 mm with ICMS-based touch feedback compared to 8.7 mm without. These results demonstrate that ICMS-evoked touch sensations to the hands can be used to provide force-based feedback for perceiving object properties and enable more precise grasping during closed-loop control of a robotic limb through a cortical interface.},
}

Humans
*Somatosensory Cortex/physiology/physiopathology
*Robotics/instrumentation
*Hand Strength/physiology
*Hand/physiology
*Touch/physiology
Brain-Computer Interfaces
Male
Electric Stimulation
Feedback, Sensory/physiology

@article {pmid40039500,
year = {2024},
author = {Teymourlouei, A and Hu, M and Gentili, R and Reggia, J},
title = {Functional Connectivity Methods for Multi-Class Mental Workload Classification.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782848},
pmid = {40039500},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Workload ; Brain/physiology/diagnostic imaging ; Male ; Adult ; Female ; Support Vector Machine ; },
abstract = {Recently, significant attention has been drawn to the ability of network-based features to classify EEG signals reflecting varying levels of mental workload. Such features are based on methods of functional connectivity (FC), which quantify the statistical relationship between EEG electrode potentials. Here, we compare three FC-based feature extraction methods for the classification of mental workload from the Multi-Attribute Task Battery. The approaches used are weighted phase lag index (WPLI), imaginary coherence (IC), and layer entanglement (LE). WPLI and IC are popular methods for FC analysis. LE is a new approach which was introduced in recent literature. When classifying between three levels of workload, a support vector machine classifier achieved an 88% average (person-dependent) accuracy using all FC methods together, 89% using only the LE method, 67% with the IC method, and 61% with the WPLI method. When classifying between two levels of workload, these scores improve to 97%, 97%, 86%, and 81%, respectively. These results support and extend the findings of prior work and suggest that LE-based methods may enable accurate mental workload prediction which is suitable for passive brain-computer interfaces.},
}

Humans
*Electroencephalography/methods
*Workload
Brain/physiology/diagnostic imaging
Male
Adult
Female
Support Vector Machine

@article {pmid40039452,
year = {2024},
author = {N, GR and Guha, D and Mahadevappa, M},
title = {EEG Artifact Removal using Stacked Multi-Head Attention Transformer Architecture.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-6},
doi = {10.1109/EMBC53108.2024.10782044},
pmid = {40039452},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Artifacts ; *Signal Processing, Computer-Assisted ; Deep Learning ; Algorithms ; Head/physiology ; },
abstract = {This study presents a transformer attention model with stacked multi-head attention layer designed to remove noise from electroencephalogram (EEG) signals, specifically addressing the problem of signal distortion caused by artifacts such as ocular and muscular noise. This is a crucial step in improving the efficacy of EEG, for disease diagnostics and BCI applications. Deep learning (DL) models have been increasingly employed for denoising EEG data in recent years, demonstrating comparable performance to classical approaches. However, the current models have been unsuccessful in capturing temporal long-term dependencies to efficiently eliminating ocular and muscular abnormalities. In this study, we address those challenges faced in the DL models by introducing multiple multi-head attention layers in the transformer model, which surpass the performance measures of previous works in EEGdenoiseNet dataset.},
}

*Electroencephalography/methods
Humans
*Artifacts
*Signal Processing, Computer-Assisted
Deep Learning
Algorithms
Head/physiology

@article {pmid40039435,
year = {2024},
author = {Chen, J and Xia, Y and Thomas, A and Carlson, T and Zhao, H},
title = {Mental Fatigue Classification with High-Density Diffuse Optical Tomography: A Feasibility Study.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782566},
pmid = {40039435},
issn = {2694-0604},
mesh = {Humans ; *Tomography, Optical/methods ; *Feasibility Studies ; *Mental Fatigue/physiopathology/diagnostic imaging ; *Support Vector Machine ; Male ; Adult ; Female ; Spectroscopy, Near-Infrared/methods ; Young Adult ; },
abstract = {High-Density Diffuse Optical Tomography (HD-DOT) presents as a promising tool for not only clinical use but also daily monitoring of mental states. This study employed wearable HD-DOT to evaluate mental fatigue, specifically examining the differences in functional near-infrared spectroscopy (fNIRS) data between states of low and high fatigue among healthy participants for data collection. Data processing involved filtering, channel selection, and dimensionality reduction through Uniform Manifold Approximation (UMAP) and Projection, followed by classification using Support Vector Machines (SVM). We developed two models to assess the accuracy and generalizability of our findings: one based on individually tailored models and another employing a leave-one-participant-out cross-validation strategy. We evaluated different kernel functions, resulting in various accuracy, F1 score, and Area Under the Curve (AUC) metrics. The study achieved an average accuracy of approximately 90% for participant-specific classifiers, underscoring the effectiveness of our approach to differentiate between low and high states of mental fatigue. Our analyses led to a robust model demonstrating high classification accuracy, proving its suitability and potential for real-time Brain-Computer Interface (BCI) applications.},
}

Humans
*Tomography, Optical/methods
*Feasibility Studies
*Mental Fatigue/physiopathology/diagnostic imaging
*Support Vector Machine
Male
Adult
Female
Spectroscopy, Near-Infrared/methods
Young Adult

@article {pmid40039431,
year = {2024},
author = {Ziegelman, L and Hernandez, ME},
title = {Application of a Neural ODE to Classify Motion Control Strategy using EEG.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782326},
pmid = {40039431},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; Male ; Adult ; Female ; Brain-Computer Interfaces ; Wrist/physiology ; Young Adult ; },
abstract = {Speed-accuracy trade offs exist in a variety of functional tasks, which may require differences in control strategies in future neuroprosthetic devices. It is the goal of this work to evaluate the predictability of different motor control strategies during wrist rotation tasks. Participants were asked to perform a series of discrete wrist rotations. This motion data was clustered into segments of either speed or range of motion oriented control strategy, controlling for age cohort and motion type. Competing neural ordinary differential equation (NODE) and random forest (RF) models were evaluated to explore the feasibility of classifying control strategy using cortical data alone. In comparison to traditional ML techniques, such as RF models, the NODE model provided achieved comparable classification accuracy at a fraction of the time. Furthermore, the use of a single motor cluster or two frontal clusters provided similar accuracy to the full data from 4 clusters, which may due to increased information from these cortical areas. This study provided a promising initial demonstration of the benefits of NODE models for future brain-computer-interface applications that require near real-time classification.},
}

Humans
*Electroencephalography/methods
Male
Adult
Female
Brain-Computer Interfaces
Wrist/physiology
Young Adult

@article {pmid40039415,
year = {2024},
author = {Flores, C and Casas, P and de Carvalho, SN and Attux, R},
title = {Advancing SSVEP-BCI Decoding: Cross-Subject Transfer Learning and Short Calibrated Approach with ELM-AE.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782739},
pmid = {40039415},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; *Evoked Potentials, Visual/physiology ; *Machine Learning ; Calibration ; Algorithms ; Signal Processing, Computer-Assisted ; Adult ; Male ; },
abstract = {The Steady-State Visually Evoked Potential (SSVEP) is a robust paradigm for developing a high-speed Brain-Computer Interface (BCI). However, one of the challenges of BCI is to face the variability of EEG signals between subjects to reduce or eliminate the time calibration process for a new subject (target subject). Some approaches propose linearly transforming; however, it limits the ability to capture complex and nonlinear relationships in data. This study presents a method for performing a Nonlinear Transformation (NLT) using an Extreme Learning Machine Autoencoder (ELM-AE) on SSVEP trials. To improve the NLT, it maps each trial from the existing subjects (source subjects) to one or a few templates from the target subject. This approach can enhance cross-subject recognition classification, reducing the calibration time for the target subject. Our results reported that, for one template, NLT and LST achieved 84.23% and 82.19% average recognition accuracy, respectively. Thus, our results reported that the recognition accuracy of NLT outperformed LST for all template sizes across all 35 subjects. These results demonstrated the feasibility of the NLT using one or a few templates for rapid calibration for the target subject.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
*Evoked Potentials, Visual/physiology
*Machine Learning
Calibration
Algorithms
Signal Processing, Computer-Assisted
Adult
Male

@article {pmid40039404,
year = {2024},
author = {Rabbito, R and Cinanni, A and Bussi, L and Guiot, C and Roatta, S},
title = {A neuro-feedback prototype based on transcranial Doppler ultrasound for brain computer interface applications.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782446},
pmid = {40039404},
issn = {2694-0604},
mesh = {Humans ; *Ultrasonography, Doppler, Transcranial/methods ; *Brain-Computer Interfaces ; Adult ; Male ; Neurofeedback/methods ; Female ; Middle Cerebral Artery/diagnostic imaging/physiology ; },
abstract = {This study proposes a TCD-based neurofeedback system designed to visualize interhemispheric hemodynamic imbalance based on the bilateral monitoring of middle cerebral arteries (MCAs). The difference between cerebral blood velocities collected from the right and left side is calculated in real time and used to drive the horizontal position of the ball displayed on a screen. With this visual feedback, the user may see how different thoughts impact on the position of the ball and possibly acquire and improve control of the ball through progressive training. Four healthy volunteers participated in a preliminary assessment conducted over four training sessions, on average demonstrating increased control over the ball movement. The results provide a proof of concept of the methodology, confirm the feasibility of the approach. The system's novelty lies in its simplicity, cost-effectiveness, and focus on cerebral lateralization, which make TCD an intriguing alternative to other neurofeedback systems, typically based on EEG, fMRI or fNIRS. The results encourage larger sample size, investigations on the TCD-based neurofeedback's therapeutic and rehabilitative potential.},
}

Humans
*Ultrasonography, Doppler, Transcranial/methods
*Brain-Computer Interfaces
Adult
Male
Neurofeedback/methods
Female
Middle Cerebral Artery/diagnostic imaging/physiology

@article {pmid40039400,
year = {2024},
author = {Kondo, S and Tanaka, H},
title = {High-Frequency SSVEP-BCI Stimulation Frequency Optimization Based on BCI accuracy.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782291},
pmid = {40039400},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Evoked Potentials, Visual/physiology ; *Algorithms ; Electroencephalography/methods ; Male ; Photic Stimulation ; },
abstract = {This study investigates optimization of the stimulation frequency of blinking stimuli used for steady-state visual evoked potential (SSVEP) brain-computer interface (BCI) for individuals. Heare, we set the target BCI accuracy to 90%, and we propose and evaluate an efficient algorithm to search for stimulation frequencies that satisfy the accuracy target for each subject. The results of a four-input SSVEP-BCI operation experiment with various stimulation frequencies indicate that the experimental system obtained optimal stimulation frequency for the subject based on BCI accuracy. However, we found that the optimization time was greater for subjects who are not proficient at BCI operations, which caused subject fatigue.},
}

Humans
*Brain-Computer Interfaces
*Evoked Potentials, Visual/physiology
*Algorithms
Electroencephalography/methods
Male
Photic Stimulation

@article {pmid40039379,
year = {2024},
author = {Lim, J and Wang, PT and Joon Sohn, W and Serrano-Amenos, C and Ibrahim, M and Lin, D and Thaploo, S and Shaw, SJ and Armacost, M and Gong, H and Lee, B and Lee, D and Andersen, RA and Heydari, P and Liu, CY and Nenadic, Z and Do, AH},
title = {Early feasibility of an embedded bi-directional brain-computer interface for ambulation.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782271},
pmid = {40039379},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Walking ; Feasibility Studies ; Spinal Cord Injuries/rehabilitation/physiopathology ; Robotics/instrumentation/methods ; Exoskeleton Device ; Gait/physiology ; },
abstract = {Current treatments for paraplegia induced by spinal cord injury (SCI) are often limited by the severity of the injury. The accompanying loss of sensory and motor functions often results in reliance on wheelchairs, which in turn causes reduced quality of life and increased risk of co-morbidities. While brain-computer interfaces (BCIs) for ambulation have shown promise in restoring or replacing lower extremity motor functions, none so far have simultaneously implemented sensory feedback functions. Additionally, many existing BCIs for ambulation rely on bulky external hardware that make them ill-suited for non-research set-tings. Here, we present an embedded bi-directional BCI (BDBCI), that restores motor function by enabling neural control over a robotic gait exoskeleton (RGE) and delivers sensory feedback via direct cortical electrical stimulation (DCES) in response to RGE leg swing. A first demonstration with this system was performed with a single subject implanted with electrocorticography electrodes, achieving an average lag-optimized cross-correlation of 0.80±0.08 between cues and decoded states over 5 runs.},
}

*Brain-Computer Interfaces
Humans
*Walking
Feasibility Studies
Spinal Cord Injuries/rehabilitation/physiopathology
Robotics/instrumentation/methods
Exoskeleton Device
Gait/physiology

@article {pmid40039323,
year = {2024},
author = {Kasprzak, H and Niewinska, N and Komendzinski, T and Otake-Matsuura, M and Rutkowski, TM},
title = {Improving the Classification of Olfactory Brain-Computer Interface Responses by Combining EEG and EBG Signals.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782826},
pmid = {40039323},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; *Electroencephalography/methods ; Male ; Adult ; Smell/physiology ; Female ; Algorithms ; Signal Processing, Computer-Assisted ; },
abstract = {The sense of smell, or olfaction, can enhance brain-computer interfaces (BCIs). Different scents can be assigned to specific commands to allow users to interact with technology naturally, but challenges remain. Accurate odor delivery systems and robust algorithms for detecting and interpreting brain activity patterns are necessary. We propose combining electroencephalography (EEG) and electrobulbography (EBG) to improve classification accuracy. Our pilot study shows promising results for a new olfactory brain-computer interface (BCI) modality that combines common spatial pattern (CSP) filtration applied to EEG and EBG to classify responses to six scent stimuli in a classical oddball paradigm.},
}

Humans
*Brain-Computer Interfaces
*Electroencephalography/methods
Male
Adult
Smell/physiology
Female
Algorithms
Signal Processing, Computer-Assisted

@article {pmid40039276,
year = {2024},
author = {Lim, RY and Jiang, M and Ang, KK and Lin, X and Guan, C},
title = {Brain-Computer-Brain system for individualized transcranial alternating current stimulation with concurrent EEG recording: a healthy subject pilot study.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782251},
pmid = {40039276},
issn = {2694-0604},
mesh = {Humans ; *Transcranial Direct Current Stimulation/methods ; Pilot Projects ; *Electroencephalography/methods ; *Brain-Computer Interfaces ; Male ; Adult ; Female ; Motor Cortex/physiology ; Young Adult ; Healthy Volunteers ; },
abstract = {In this study, we introduce a novel brain-computer-brain (BCB) system to investigate the aftereffects of individualized, task-dependent transcranial alternating current stimulation (tACS) delivered to the motor cortex. While previous studies utilized either a generic stimulation frequency or matched it to an individual's resting frequency (e.g. individual alpha frequency, iAF), our study employed a trial-by-trial tACS stimulation design wherein the stimulation frequency delivered matches the individual's peak motor imagery (MI) performance frequency. 14 healthy subjects participated in both tACS and tACS-sham on separate days in a within-subject, randomized controlled design. We found that active tACS delivered to subjects receiving alpha (α)-tACS resulted in a decline in MI performance while that with tACS-sham did not differ significantly from baseline. However, subjects receiving beta (β)-tACS showed no significant difference in effect for both active tACS and tACS-sham conditions. These findings indirectly corroborated with that from literature advocating the notion of α tACS as functionally inhibitory; hence the consequential deterioration of MI performance observed only in α-tACS subjects. A more conclusive analysis will be conducted once more data is collected from this ongoing study.Clinical Relevance: The results gathered suggest the differential functional significance of α- and β-tACS in an individualized MI task-specific tACS delivery to the motor cortex with concurrent EEG recording. Although insignificant at the point of data analysis where sample size is small in this ongoing study, tACS-sham (30 Hz) seemed to potentially modulate neural oscillations in the direction of improving MI performance. These findings can inform future tACS study designs based on a system with personalized stimulation delivery for MI task investigations within laboratory and clinical settings - potentially beneficial towards upper limb stroke rehabilitation.},
}

Humans
*Transcranial Direct Current Stimulation/methods
Pilot Projects
*Electroencephalography/methods
*Brain-Computer Interfaces
Male
Adult
Female
Motor Cortex/physiology
Young Adult
Healthy Volunteers

@article {pmid40039273,
year = {2024},
author = {Jiang, H and Xiao, X and Mei, J and Xu, M and Wang, K and Ming, D},
title = {A Novel Real-time Algorithm Based on Phase-Locked Data Alignment for Continuously Controlled SSVEP-BCI.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782824},
pmid = {40039273},
issn = {2694-0604},
mesh = {Humans ; *Algorithms ; *Brain-Computer Interfaces ; *Evoked Potentials, Visual/physiology ; *Electroencephalography/methods ; Adult ; Male ; Female ; },
abstract = {OBJECTIVE: Brain-computer interfaces (BCIs) based on steady-state visual evoked potential (SSVEP) show good performance. However, algorithms always decode segments of electroencephalogram (EEG) and can only satisfy discrete output instructions, which limit the real-time continuous control of the BCI system. This article proposes a novel algorithm for SSVEP-BCI that can translate continuous EEG into control commands, achieving real-time monitoring of user intentions.

METHODS: A phase synchronicity maximum strategy has been employed in this algorithm, which could capture a fixed-duration SSVEP epoch near any given moment, ensuring each trial is aligned with the phase of the potential corresponding template. Then, the algorithm utilized an update strategy of a small-step sliding window to recognize and output commands in approximately real-time.

RESULTS: We constructed an SSVEP-BCI system with continuous stimulation and recruited nine subjects. The results showed that the algorithm proposed in this study efficiently decoded continuously evoked SSVEP signals. The BCI's online average accuracy and ITR were 92.03% and 143.38 bits/min, respectively.

SIGNIFICANCE: The proposed algorithm can decode SSVEP at any time theoretically, which improves command output density as well as maintains high recognition accuracy. This study provides novel methods for real-time control of external devices using SSVEP-BCIs and helps to develop BCIs that are more compatible with human control habits.},
}

Humans
*Algorithms
*Brain-Computer Interfaces
*Evoked Potentials, Visual/physiology
*Electroencephalography/methods
Adult
Male
Female

@article {pmid40039271,
year = {2024},
author = {Umezawa, K and Isezaki, T and Okitsu, K and Yokoyama, O and Suzuki, M and Nishimura, Y},
title = {Refined Force Estimation in Monkey's Pinching Tasks Through Integrated EMG and ECoG Data: A Kalman Filter Method.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782574},
pmid = {40039271},
issn = {2694-0604},
mesh = {*Electromyography/methods ; Animals ; *Brain-Computer Interfaces ; Electrocorticography/methods ; Algorithms ; Macaca mulatta ; },
abstract = {In the development of brain-computer interfaces (BCIs), precise decoding of motor outputs is crucial. This study presents an enhanced Kalman filter approach that integrates electromyography (EMG) with electrocorticography (ECoG) to improve force estimation in pinching tasks. By incorporating EMG data as a state variable in the filter, we aim to account for musculoskeletal dynamics, enhancing the accuracy of force predictions. This integration significantly improves the decoding performance, particularly during dynamic force phases. The results confirm the importance of embedding musculoskeletal dynamics into ECoG-based BCIs, which may help improve prosthetic control and motor rehabilitation for people with motor impairments.},
}

*Electromyography/methods
Animals
*Brain-Computer Interfaces
Electrocorticography/methods
Algorithms
Macaca mulatta

@article {pmid40039264,
year = {2024},
author = {Li, M and Pun, SH and Chen, F},
title = {Cross-paradigm data alignment to improve the calibration of asynchronous BCI systems in EEG-based speech imagery.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781999},
pmid = {40039264},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Brain-Computer Interfaces ; Calibration ; Speech/physiology ; Algorithms ; },
abstract = {The brain-computer interfaces (BCIs) based on speech imagery with asynchronous (self-paced) paradigms enable users to directly access and manipulate BCIs with more freedom. Compared with the indirect BCIs with traditional synchronous (cue-based) paradigms, the calibration time of asynchronous paradigms was much longer and with the unbalanced number of task states and idle states. This work aimed to improve the calibration of asynchronous BCI systems by applying a data alignment (DA) approach on cue-based and self-paced paradigms. The cue-based paradigm was regarded as the calibration paradigm and the self-paced paradigm was the testing paradigm. The data alignment approach based on the parallel transport mapped their features on the same tangent space. The logistic regression was used as the classifier to classify task states and idle states. The average result with DA was 7.52% higher than that without DA (baseline), which were 78.45% and 70.92%, respectively. Specially, the best classification accuracy was for 91.82% with DA, and the largest improvement in accuracy was 22.92%. These results suggest that it is practical to use a synchronous paradigm as calibration paradigm in asynchronous BCI systems and the data alignment approach has positive impacts on the classification of task states and idle states.},
}

*Electroencephalography/methods
Humans
*Brain-Computer Interfaces
Calibration
Speech/physiology
Algorithms

@article {pmid40039208,
year = {2024},
author = {Geng, Y and Yang, B and Ke, S and Chang, L and Zhang, J and Zheng, Y},
title = {Motor Imagery Decoding from EEG under Visual Distraction via Feature Map Attention EEGNet.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781898},
pmid = {40039208},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Brain-Computer Interfaces ; Attention/physiology ; Imagination/physiology ; Male ; Adult ; Signal Processing, Computer-Assisted ; },
abstract = {The investigation of motor imagery (MI)-based brain-computer interface (BCI) is vital to the domains of human-computer interaction and rehabilitation. Few existing studies on electroencephalogram(EEG) signals decoding based on MI consider any distractions. However, it is difficult for users to do a single MI task in real life, which is especially affected by visual distraction. In this paper, we aim to investigate the effects of visual distraction on MI decoding performance. We first design a noval MI paradigm under visual distraction and observe distinct patterns of event-related desynchronization (ERD) and event-related synchronization (ERS) in MI under visual distraction. Then, we propose a robust decoding method of MI under visual distraction from EEG signals by using the feature map attention EEGNet (named FMA-EEGNet) and use EEG data under conditions without and with distraction to compare the decoding performance of five methods (including the proposed method and other methods). The results demonstrate that FMA-EEGNet achieved mean accuracy of 89.1% and 82.2% without and with visual distraction, respectively, indicating superior performance compared to other methods while exhibiting minimal degradation in performance. This work contributes significantly to the advancement of practical applications in MI-BCI technology.},
}

Humans
*Electroencephalography/methods
*Brain-Computer Interfaces
Attention/physiology
Imagination/physiology
Male
Adult
Signal Processing, Computer-Assisted

@article {pmid40039201,
year = {2024},
author = {Li, Q and Zhang, Z and Shi, M and Tao, X},
title = {Multi-channel Neural Signal Recording System for an Implantable Brain-Computer Interface.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782545},
pmid = {40039201},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; Signal Processing, Computer-Assisted ; Electroencephalography/instrumentation ; Equipment Design ; Brain/physiology ; },
abstract = {Simultaneous recordings of neural activity at massive scope, in the long term, and under bio-safety conditions, could provide crucial information, which helps in better understanding the operation mechanism of the brain and promotes the clinical application evolution for the brain-computer interface. For this purpose, a multi-channel neural signal recording system is presented, which can record up to 2048-channel neural signals by multiple connections of a customized collection system. The system consists of a sensor array module, a central controller module, and an upper computer module. Using the modular design method, the sensor array module can be contrived by changing the number of channels. The single-channel data acquisition module has a sampling resolution of 16 bits, and a sampling rate of 30 KSamples/s. The central controller module can establish a connection between the sensor array module and the upper computer module, and control their operations. The upper computer module can display the data results. The system verifies the performance of the multi-channel data acquisition through the analog neural signal.},
}

*Brain-Computer Interfaces
Humans
Signal Processing, Computer-Assisted
Electroencephalography/instrumentation
Equipment Design
Brain/physiology

@article {pmid40039185,
year = {2024},
author = {Raghavan, V and Patel, P and He, X and Mesgarani, N},
title = {Decoding auditory attention for real-time BCI control.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-6},
doi = {10.1109/EMBC53108.2024.10782575},
pmid = {40039185},
issn = {2694-0604},
mesh = {Humans ; *Brain-Computer Interfaces ; Electroencephalography ; Attention/physiology ; Acoustic Stimulation ; Auditory Perception/physiology ; Male ; },
abstract = {Brain-Computer Interfaces (BCI) facilitate interaction with devices, enhancing the quality of life for individuals with disabilities and offering a more direct method for controlling smart devices. Auditory BCIs commonly utilize event-related potentials (ERPs) necessitating a sequential presentation of choices through auditory stimuli. However, such methods impose constraints on the achievable Information Transfer Rate (ITR) compared to visual BCIs due to extended stimulus presentation times. Here, we introduce an auditory BCI approach in which the selective representation of attended speech in a listener's brain enables the decoding of one target sound source from the background. The simultaneous delivery of options in our proposed method reduces presentation durations by 2.5x compared to previous auditory BCI paradigms. This approach yields an average ITR exceeding 17 bits/min, with the best subject surpassing 33 bits/min. By outdoing current state-of-the-art auditory BCI paradigms, our research represents a significant advancement in the development of practical auditory BCI technologies.},
}

Humans
*Brain-Computer Interfaces
Electroencephalography
Attention/physiology
Acoustic Stimulation
Auditory Perception/physiology
Male

@article {pmid40039137,
year = {2024},
author = {Cinquetti, E and Siviero, I and Babiloni, F and Menegaz, G and Storti, SF},
title = {Passive BCI Towards Health and Safety in Industry: Forecasting Human Vigilance 5.5 s Ahead.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782689},
pmid = {40039137},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Brain-Computer Interfaces ; Male ; Adult ; Female ; Industry ; Forecasting ; Deep Learning ; },
abstract = {Brain-computer interfaces based on electroencephalography (EEG) recordings are gaining increasing interest in the industrial domain, aiming to enhance health, safety and performance by optimizing the cognitive load of industrial operators and facilitating human-robot interactions. This study introduces a novel experimental protocol and analysis pipeline for predicting vigilance degradation during repetitive tasks. A dataset was recorded from 10 volunteers who observed a robotic arm executing three distinct movements. The EEG power spectrum was analyzed over time using the continuous wavelet transform. Upon verifying the increased amplitude of EEG oscillations in the 8-12 Hz frequency band, we forecast its behaviour, comparing the vector autoregressive model with two deep learning recurrent architectures. The proposed encoder-decoder gated recurrent unit model obtained accurate forecasts (mean absolute error = 0.048, R[2] = 0.726) up to 5.5 s into the future. The findings suggested the feasibility of vigilance monitoring in the Industry 5.0 framework, proposing a strategy to prevent human accidents and performance decline during monotonous activities.},
}

Humans
*Electroencephalography/methods
*Brain-Computer Interfaces
Male
Adult
Female
Industry
Forecasting
Deep Learning

@article {pmid40039126,
year = {2024},
author = {Amrani, H and Micucci, D and Nalin, M and Napoletano, P and Rizzi, I},
title = {EEG Acquisition and Motor Imagery Classification for Robotic Control.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782723},
pmid = {40039126},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Robotics/instrumentation ; *Brain-Computer Interfaces ; Support Vector Machine ; Movement/physiology ; Imagination/physiology ; },
abstract = {The adoption of brain-computer interfaces (BCIs) has significantly increased in various application domains, particularly in the field of controlling robotic systems through motor imagery. The article contributes in two primary ways: 1) validating the effectiveness of using a minimally invasive electroencephalography (EEG) device combined with machine learning techniques to control fundamental movements in a robotic setting, and 2) demonstrating these findings practically through the construction of a robotic vehicle. In this vehicle, tasks involving motor imagery align directly with control commands for the vehicle. To validate our approach, we identified four-class and two-class classification tasks. The signals have been acquired from a portable EEG device equipped with eight dry electrodes. We employed sliding window strategies to segment the data, along with feature extraction using the Common Spatial Pattern (CSP) method. Classification modules were implemented based on Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) models. The experimentation involved five participants, each with their own personalized model. While the accuracy of results in the four-class tasks is not notably high, the outcomes in binary classification tasks are promising, boasting an average accuracy of approximately 61%. Results suggest a promising potential for this approach in the realm of robot control, particularly when employing dry-electrode EEG devices.},
}

*Electroencephalography/methods
Humans
*Robotics/instrumentation
*Brain-Computer Interfaces
Support Vector Machine
Movement/physiology
Imagination/physiology

@article {pmid40039119,
year = {2024},
author = {Rajpura, P and Meena, YK},
title = {Towards Optimising EEG Decoding using Post-hoc Explanations and Domain Knowledge.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10781846},
pmid = {40039119},
issn = {2694-0604},
mesh = {*Electroencephalography/methods ; Humans ; *Brain-Computer Interfaces ; Signal Processing, Computer-Assisted ; },
abstract = {Decoding Electoencephalography (EEG) during motor imagery is pivotal for the Brain-Computer Interface (BCI) system, influencing its overall performance significantly. As end-to-end data-driven learning methods advance, the challenge lies in balancing model complexity with the need for human interpretability and trust. Despite strides in EEG-based BCIs, challenges like artefacts and low signal-to-noise ratio emphasise the ongoing importance of model transparency. This work proposes using post-hoc explanations to interpret model outcomes and validate them against domain knowledge. Leveraging the GradCAM post-hoc explanation technique on the EEG motor movement/imagery dataset, this work demonstrates that relying solely on accuracy metrics may be inadequate to ensure BCI performance and acceptability. A model trained using all EEG channels of the dataset achieves 72.60% accuracy, while a model trained with motor-imagery/movement-relevant channel data has a statistically insignificant decrease of 1.75%. However, the relevant features for both are very different based on neurophysiological facts. This work demonstrates that integrating domain-specific knowledge with Explainable AI (XAI) techniques emerges as a promising paradigm for validating the neurophysiological basis of model outcomes in BCIs. Our results reveal the significance of neurophysiological validation in evaluating BCI performance, highlighting the potential risks of exclusively relying on performance metrics when selecting models for dependable and transparent BCIs.},
}

*Electroencephalography/methods
Humans
*Brain-Computer Interfaces
Signal Processing, Computer-Assisted

@article {pmid40039013,
year = {2024},
author = {Cetera, A and Rabiee, A and Ghafoori, S and Shahriari, Y and Abiri, R},
title = {Classification of Emerging Neural Activity from Planning to Grasp Execution using a Novel EEG-Based BCI Platform.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782523},
pmid = {40039013},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Brain-Computer Interfaces ; *Hand Strength/physiology ; Support Vector Machine ; Male ; Adult ; },
abstract = {There have been different reports of developing Brain-Computer Interface (BCI) platforms to investigate the noninvasive electroencephalography (EEG) signals associated with plan-to-grasp tasks in humans. However, these reports were unable to clearly show evidence of emerging neural activity from the planning (observation) phase - dominated by the vision cortices - to grasp execution - dominated by the motor cortices. In this study, we developed a novel vision-based-grasping BCI platform that distinguishes different grip types (power and precision) through the phases of plan-to-grasp tasks using EEG signals. Using our platform and extracting features from Filter Bank Common Spatial Patterns (FBCSP), we show that frequency-band specific EEG contains discriminative spatial patterns present in both the observation and movement phases. Support Vector Machine (SVM) classification (power vs precision) yielded high accuracy percentages of 74% and 68% for the observation and movement phases in the alpha band, respectively.},
}

Humans
*Electroencephalography/methods
*Brain-Computer Interfaces
*Hand Strength/physiology
Support Vector Machine
Male
Adult

@article {pmid40038999,
year = {2024},
author = {Farabbi, A and Mainardi, L},
title = {Advancing Brain-Computer Interface Systems: Asynchronous Classification of Error Potentials.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782785},
pmid = {40038999},
issn = {2694-0604},
mesh = {*Brain-Computer Interfaces ; Humans ; *Electroencephalography/methods ; Discriminant Analysis ; Brain/physiology ; Algorithms ; Signal Processing, Computer-Assisted ; },
abstract = {This paper explores the paradigm shift in the classification of Error-Related Potentials (ErrP) in Brain-Computer Interfaces (BCIs) by introducing an asynchronous approach. Traditional synchronous methods, relying on precise temporal alignment between stimuli presentation and neural responses, face challenges in real-world scenarios with human response variability.The proposed asynchronous classification liberates BCI systems from strict temporal constraints, allowing for a more natural interaction paradigm. The study introduces an innovative ensemble method comprising Linear Discriminant Analysis (LDA) and EEGNet for asynchronous ErrP classification.The method is evaluated on EEG data from the BNCI Horizon 2020 dataset, demonstrating high balanced accuracy. While the introduction of EEGNet refines the classification, reducing false positives, challenges persist in achieving a balanced trade-off between precision and recall.The findings suggest the ensemble method's potential for practical applications, emphasizing the need for further refinement and exploration of advanced techniques in asynchronous ErrP classification.},
}

*Brain-Computer Interfaces
Humans
*Electroencephalography/methods
Discriminant Analysis
Brain/physiology
Algorithms
Signal Processing, Computer-Assisted

@article {pmid40038985,
year = {2024},
author = {Lee, KY and Chang, KY and Hsu, HC and Tseng, YT and Wei, CS and Lin, SS and Chuang, CH},
title = {Utilizing Motor-Imagery Brain-Computer Interfaces for the Assessment of Developmental Coordination Disorder in Children.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781534},
pmid = {40038985},
issn = {2694-0604},
mesh = {Humans ; *Motor Skills Disorders/diagnosis/physiopathology ; *Brain-Computer Interfaces ; Child ; *Electroencephalography/methods ; Male ; Female ; Imagination/physiology ; },
abstract = {Developmental Coordination Disorder (DCD) is a neurodevelopmental disorder characterized by significant motor difficulties that affect daily life. Current assessment methods primarily focus on behavioral analysis, lacking in neuroscientific metrics for a comprehensive evaluation. This study introduced an electroencephalography-based motor imagery brain-computer interface classification system for evaluating children with DCD. A key of this system was the implementation of entropy-based data screening, which markedly enhanced classification performance. Notably, using mu band power in a support vector machine achieved an accuracy rate of 79.0%. These findings pave the way for developing a tool that could assist professionals in identifying children potentially affected by DCD.},
}

Humans
*Motor Skills Disorders/diagnosis/physiopathology
*Brain-Computer Interfaces
Child
*Electroencephalography/methods
Male
Female
Imagination/physiology

@article {pmid40038962,
year = {2024},
author = {Sreekantham, S and Chetty, N and Weber, DJ},
title = {Detecting and Eliminating Cardiac Artifact from Endovascular EEG Signals.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10782938},
pmid = {40038962},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Artifacts ; *Signal Processing, Computer-Assisted ; Brain-Computer Interfaces ; Heart/physiology/physiopathology ; },
abstract = {Paralysis is a debilitating condition that affects more than 5.4 million people in the U.S. In severe cases, the paralyzed patient is incapable of communication. Restoring this communication is a primary goal of caretakers and is critical to improving the patient's quality of life. Brain-computer interfaces (BCIs) that directly access signals from the motor cortex are a promising method of circumventing the condition causing paralysis, typically using machine learning (ML) to predict motor intent from brain signals. However, BCIs are highly invasive and subjects have primarily been limited to patients with mild to moderate paralysis. The Stentrode is a novel technology that records electroencephalographic (EEG) signals via an electrode array placed endovascularly in the superior sagittal sinus. The first clinical trials of this technology aim to enable digital communication for severely paralyzed patients, translating brain signals from attempted movements into computer control inputs like mouse clicks. However, recordings of EEG are often contaminated with artifacts, including biopotentials arising from other excitable tissues, such as the heart and skeletal muscle. This study characterizes the electrocardiographic (ECG) artifact detected in the Stentrode recordings and proposes an automated Independent Component Analysis (ICA) method for removing this artifact. We compare the effectiveness of this method to previous methods for removal. Quantifying and eliminating the cardiac artifact is critical to accurately decode signals from the motor cortex and restore patients' ability to communicate.},
}

Humans
*Electroencephalography/methods
*Artifacts
*Signal Processing, Computer-Assisted
Brain-Computer Interfaces
Heart/physiology/physiopathology

@article {pmid40038951,
year = {2024},
author = {Song, Z and Zhang, X and Tan, J and Wang, M and Wang, Y},
title = {Facilitating Knowledge Transfer: An Approach for Matching Neural Patterns between Motor Tasks.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781969},
pmid = {40038951},
issn = {2694-0604},
mesh = {Rats ; *Brain-Computer Interfaces ; Animals ; Algorithms ; },
abstract = {Brain-machine interface (BMI) holds great promise for restoring the impaired motor functions of individuals. In real-life scenarios, BMI users often face the challenge of quickly learning new tasks to adapt to complex environments. Consequently, it becomes essential to investigate the transferability of knowledge (neural-action mapping) of the decoder gained from previously learned tasks to new tasks. This paper introduces an approach for matching neural patterns between motor tasks to facilitate knowledge transfer, which is a key step in facilitating knowledge transfer. We project neural data into a 6D jPCA feature space and observe that neural patterns associated with the same action are preserved in the last four dimensions. By utilizing the decoder trained from the previous task, we obtain a prior estimate of the matched class. This prior estimate is further refined by clustering the neural patterns in the first two dimensions, as the data demonstrates distinct cluster shapes. To validate our approach, we conducted an experiment where a rat learned two related motor tasks sequentially. The preliminary results showed that our proposed method achieved an accuracy of 87.04% in estimating the matched class compared to the ground truth. In contrast, utilizing the decoder trained from the previous task within the entire jPCA space resulted in a significantly lower accuracy of merely 39.8%. These findings highlight the efficacy of our proposed method in matching neural patterns between motor tasks, thus facilitating knowledge transfer.},
}

Rats
*Brain-Computer Interfaces
Animals
Algorithms

@article {pmid40038942,
year = {2024},
author = {Rabiee, A and Ghafoori, S and Cetera, A and Shahriari, Y and Abiri, R},
title = {Wavelet Analysis of Noninvasive EEG Signals Discriminates Complex and Natural Grasp Types.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-5},
doi = {10.1109/EMBC53108.2024.10782674},
pmid = {40038942},
issn = {2694-0604},
mesh = {Humans ; *Electroencephalography/methods ; *Wavelet Analysis ; *Hand Strength/physiology ; *Brain-Computer Interfaces ; Adult ; Male ; Female ; Signal Processing, Computer-Assisted ; Young Adult ; Machine Learning ; },
abstract = {This research aims to decode hand grasps from Electroencephalograms (EEGs) for dexterous neuroprosthetic development and Brain-Computer Interface (BCI) applications, especially for patients with motor disorders. Particularly, it focuses on distinguishing two complex natural power and precision grasps in addition to a neutral condition as a no-movement condition using a new EEG-based BCI platform and wavelet signal processing. Wavelet analysis involved generating time-frequency and topographic maps from wavelet power coefficients. Then, by using machine learning techniques with novel wavelet features, we achieved high average accuracies: 85.16% for multiclass, 95.37% for No-Movement vs Power, 95.40% for No-Movement vs Precision, and 88.07% for Power vs Precision, demonstrating the effectiveness of these features in EEG-based grasp differentiation. In contrast to previous studies, a critical part of our study was permutation feature importance analysis, which highlighted key features for grasp classification. It revealed that the most crucial brain activities during grasping occur in the motor cortex, within the alpha and beta frequency bands. These insights demonstrate the potential of wavelet features in real-time neuroprosthetic technology and BCI applications.},
}

Humans
*Electroencephalography/methods
*Wavelet Analysis
*Hand Strength/physiology
*Brain-Computer Interfaces
Adult
Male
Female
Signal Processing, Computer-Assisted
Young Adult
Machine Learning

@article {pmid40037510,
year = {2025},
author = {Bjånes, DA and Kellis, S and Nickl, R and Baker, B and Aflalo, T and Bashford, L and Chivukula, S and Fifer, MS and Osborn, LE and Christie, B and Wester, BA and Celnik, PA and Kramer, D and Pejsa, K and Crone, NE and Anderson, WS and Pouratian, N and Lee, B and Liu, CY and Tenore, F and Rieth, L and Andersen, RA},
title = {Quantifying physical degradation alongside recording and stimulation performance of 980 intracortical microelectrodes chronically implanted in three humans for 956-2246 days.},
journal = {Acta biomaterialia},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.actbio.2025.02.030},
pmid = {40037510},
issn = {1878-7568},
abstract = {The clinical success of brain computer interfaces depends on overcoming both biological and material challenges to ensure a long-term stable connection for neural recording and stimulation. This study systematically quantified damage that microelectrodes sustained during chronical implantation in three people with tetraplegia for 956-2246 days. Using scanning electron microscopy (SEM), we imaged 980 microelectrodes from eleven Neuroport arrays tipped with platinum (Pt, n=8) and sputtered iridium oxide film (SIROF, n=3). Arrays were implanted/explanted from posterior parietal, motor and somatosensory cortices across three clinical sites (Caltech/UCLA, Caltech/USC, APL/Johns Hopkins). From the electron micrographs, we quantified and correlated physical damage with functional outcomes measured in vivo, prior to explant (recording quality, noise, impedance and stimulation ability). Despite greater physical degradation, SIROF electrodes were twice as likely to record neural activity than Pt (measured by SNR). For SIROF, 1 kHz impedance significantly correlated with all physical damage metrics, recording, and stimulation performance, suggesting a reliable measurement of in vivo degradation. We observed a new degradation type, primarily on stimulated electrodes ("pockmarked" vs "cracked") electrodes; however, no significant degradation due to stimulation or amount of charge. We hypothesize erosion of the silicon shank accelerates damage to the electrode / tissue interface, following damage to the tip metal. These findings link quantitative measurements to the microelectrodes' physical condition and their capacity to record/stimulate. These data could lead to improved manufacturing or novel electrode designs to improve long-term performance of BCIs making them are vitally important as multi-year clinical trials of BCIs are becoming more common. STATEMENT OF SIGNIFICANCE: Long-term performance stability of the electrode-tissue interface is essential for clinical viability of Brain Computer Interface (BCI) devices; currently, materials degradation is a critical component for performance loss. Across three human participants, ten micro-electrode arrays (plus one control) were implanted for 956-2246 days. Using scanning electron microscopy (SEM), we analyzed degradation of 980 electrodes, comparing two types of commonly implanted electrode tip metals: Platinum (Pt) and Sputtered Iridium Oxide Film (SIROF). We correlated observed degradation with in vivo electrode performance: recording (signal-to-noise ratio, noise, impedance) and stimulation (evoked somatosensory percepts). We hypothesize penetration of the electrode tip by biotic processes leads to erosion of the supporting silicon core, which then accelerates further tip metal damage. These data could lead to improved manufacturing processes or novel electrode designs towards the goal of a stable BCI electrical interface, spanning a multi-decade participant lifetime.},
}

@article {pmid40037493,
year = {2025},
author = {Tang, G and Chen, B and Wu, M and Sun, L and Fan, R and Hou, R and Liu, W and Kang, J and Li, Y and Wang, M and Zhang, Y and Lu, N and Guo, W and Zhang, Y and Li, X and Wei, W and Yu, H and Li, T},
title = {Effectiveness of mindfulness-based cognitive therapy for treating generalized anxiety disorder and the moderating influence of abuse during childhood: A randomized controlled trial.},
journal = {Journal of affective disorders},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jad.2025.02.103},
pmid = {40037493},
issn = {1573-2517},
abstract = {BACKGROUND: Mindfulness-based cognitive therapy (MBCT) has emerged as a promising intervention for generalized anxiety disorder (GAD). This study evaluated MBCT's effectiveness for GAD and examined whether childhood maltreatment moderates its impact.

METHODS: Individuals with GAD were randomized to receive one of two 8-week interventions, either MBCT in-person or psychoeducation on-line (n = 27 per group). At baseline and after 4 and 8 weeks of intervention, both groups were assessed using the Beck Anxiety Inventory and Penn State Worry Questionnaire as well as several secondary questionnaires. Changes in the severity of anxiety and worry over time, as determined using linear mixed modeling, were compared between the two groups as a whole and among subgroups stratified according to type of maltreatment in childhood.

RESULTS: Among all participants, severity of worry decreased significantly more in the MBCT group than in the psychoeducation group, whereas severity of anxiety decreased to a similar extent in the two groups. Among individuals who had experienced emotional abuse in childhood, MBCT reduced the severity of anxiety significantly more than psychoeducation. In fact, MBCT was significantly more effective against anxiety in individuals who had experienced emotional abuse than in those who had not.

CONCLUSIONS: MBCT might be effective in alleviating worry symptoms in GAD, while its effectiveness against anxiety symptoms appears to be influenced by the history of maltreatment, particularly emotional abuse.

TRIAL REGISTRATION: ChiCTR2400087188 (Chictr.org).},
}

@article {pmid40036596,
year = {2025},
author = {Chen, Q and Huang, X and Ju, Z and Lin, H and Tang, H and Guo, C and Fan, F and Zhao, X and Ma, Y and Luo, Y and Li, W and Zhong, W and Zhao, D},
title = {A Triband Metasurface Covering Visible, Midwave Infrared, and Long-Wave Infrared for Optical Security.},
journal = {Nano letters},
volume = {},
number = {},
pages = {},
doi = {10.1021/acs.nanolett.5c00083},
pmid = {40036596},
issn = {1530-6992},
abstract = {The independent manipulation of light across multiple wavelength bands provides new opportunities for optical security. Although dual-band optical encryption methods in the visible (VIS) and infrared bands have been developed, achieving synchronized and synergistic optical security across the VIS, midwave infrared (MWIR), and long-wave infrared (LWIR) bands remains a significant challenge. Here, we experimentally demonstrate a triband metasurface that covers the VIS, MWIR, and LWIR bands. While VIS imaging is achieved by structural color, MWIR, and LWIR imaging are achieved by selective emissivity structures, with MWIR/LWIR emissivities in the MWIR imaging region of 0.81/0.17, and in the LWIR imaging region of 0.21/0.83. Importantly, the MWIR and LWIR information is completely hidden in the VIS band. We also validate the ability of metasurface to encode complex information and information-misleading encryption. This work introduces new approaches for enhancing optical security and holds significant potential for applications such as anticounterfeiting and thermal camouflage.},
}

@article {pmid40036537,
year = {2025},
author = {Ravi, A and Wolfe, P and Tung, J and Jiang, N},
title = {Signal Characteristics, Motor Cortex Engagement, and Classification Performance of Combined Action Observation, Motor Imagery and SSMVEP (CAMS) BCI.},
journal = {IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society},
volume = {PP},
number = {},
pages = {},
doi = {10.1109/TNSRE.2025.3544479},
pmid = {40036537},
issn = {1558-0210},
abstract = {Motor imagery (MI)-based Brain-Computer Interfaces (BCIs) have shown promise in engaging the motor cortex for recovery. However, individual responses to MI-based BCIs are highly variable and relatively weak. Conversely, combined action observation (AO) and motor imagery (MI) paradigms have demonstrated stronger responses compared to AO or MI alone, along with enhanced cortical excitability. In this study, a novel BCI called Combined AO, MI, and Steady-State Motion Visual Evoked Potential (SSMVEP) (CAMS) was proposed. CAMS was designed based on gait observation and imagination. Twenty-five healthy volunteers participated in the study with CAMS serving as the intervention and SSMVEP checkerboard as the control condition. We hypothesized the CAMS intervention can induce observable increases in the negativity of the movement-related cortical potential (MRCP) associated with ankle dorsiflexion. MRCP components, including Bereitschaftspotential, were measured pre- and post-intervention. Additionally, the signal characteristics of the visual and motor responses were quantified. Finally, a two-class visual BCI classification performance was assessed. A consistent increase in negativity was observed across all MRCP components in signals over the primary motor cortex, compared to the control condition. CAMS visual BCI achieved a median accuracy of 83.8%. These findings demonstrate the ability of CAMS BCI to enhance cortical excitability in relation to movement preparation and execution. The CAMS stimulus not only evokes SSMVEP-like activity and sensorimotor rhythm but also enhances the MRCP. These findings contribute to the understanding of CAMS paradigm in enhancing cortical excitability, consistent and reliable classification performance holding promise for motor rehabilitation outcomes and future BCI design considerations.},
}

@article {pmid40036449,
year = {2025},
author = {Kim, MK and Shin, HB and Cho, JH and Lee, SW},
title = {Developing Brain-Based Bare-Handed Human-Machine Interaction via On-Skin Input.},
journal = {IEEE transactions on cybernetics},
volume = {PP},
number = {},
pages = {},
doi = {10.1109/TCYB.2025.3533088},
pmid = {40036449},
issn = {2168-2275},
abstract = {Developing natural, intuitive, and human-centric input systems for mobile human-machine interaction (HMI) poses significant challenges. Existing gaze or gesture-based interaction systems are often constrained by their dependence on continuous visual engagement, limited interaction surfaces, or cumbersome hardware. To address these challenges, we propose MetaSkin, a novel neurohaptic interface that uniquely integrates neural signals with on-skin interaction for bare-handed, eyes-free interaction by exploiting human's natural proprioceptive capabilities. To support the interface, we developed a deep learning framework that employs multiscale temporal-spectral feature representation and selective feature attention to effectively decode neural signals generated by on-skin touch and motion gestures. In experiments with 12 participants, our method achieved offline accuracies of 81.95% for touch location discrimination, 71.00% for motion type identification, and 46.08% for 10-class touch-motion classification. In pseudo-online settings, accuracies reached 99.43% for touch onset detection, and 80.34% and 67.02% for classification of touch location and motion type, respectively. Neurophysiological analyses revealed distinct neural activation patterns in the sensorimotor cortex, underscoring the efficacy of our multiscale approach in capturing rich temporal and spectral dynamics. Future work will focus on optimizing the system for diverse user populations and dynamic environments, with a long-term goal of advancing human-centered, neuroadaptive interfaces for next-generation HMI systems. This work represents a significant step toward a paradigm shift in design of brain-computer interfaces, bridging sensory and motor paradigms for building more sophisticated systems.},
}

@article {pmid40035637,
year = {2025},
author = {Sun, B and Zhang, X and Zhang, X and Xu, B and Wang, Y},
title = {Data collection, enhancement, and classification of functional near-infrared spectroscopy motor execution and imagery.},
journal = {The Review of scientific instruments},
volume = {96},
number = {3},
pages = {},
doi = {10.1063/5.0236392},
pmid = {40035637},
issn = {1089-7623},
mesh = {*Spectroscopy, Near-Infrared/methods/instrumentation ; Humans ; *Brain-Computer Interfaces ; Imagination/physiology ; Electroencephalography/instrumentation/methods ; Data Collection ; Male ; Adult ; },
abstract = {Recognition and execution of motor imagery play a key role in brain-computer interface (BCI) and are prerequisites for converting thoughts into executable instructions. However, to date, data acquired through commonly used electroencephalography (EEG) methods are very sensitive to motion interference, which will affect the accuracy of the data classification. The emerging functional near-infrared spectroscopy (fNIRS) technique, while overcoming the drawbacks of EEG's susceptibility to interference and difficulty in detecting motor signals, has less publicly available data. In this paper, we designed a motor execution and imagery experiment based on a wearable fNIRS device to acquire brain signals and proposed a modified Kolmogorov-Arnold network (named SE-KAN) for recognizing fNIRS signals corresponding to the task. Due to the small number of subjects in this experiment, the Wasserstein generative adversarial network was used to enhance the data processing. For the fNIRS data recognition task, the SE-KAN method achieved 96.36 ± 2.43% single-subject accuracy and 84.72 ± 3.27% cross-subject accuracy. It is believed that the dataset and method of this paper will help the development of BCI.},
}

*Spectroscopy, Near-Infrared/methods/instrumentation
Humans
*Brain-Computer Interfaces
Imagination/physiology
Electroencephalography/instrumentation/methods
Data Collection
Male
Adult

@article {pmid40035554,
year = {2025},
author = {Khan, WU and Shen, Z and Mugo, SM and Wang, H and Zhang, Q},
title = {Implantable hydrogels as pioneering materials for next-generation brain-computer interfaces.},
journal = {Chemical Society reviews},
volume = {},
number = {},
pages = {},
doi = {10.1039/d4cs01074d},
pmid = {40035554},
issn = {1460-4744},
abstract = {Use of brain-computer interfaces (BCIs) is rapidly becoming a transformative approach for diagnosing and treating various brain disorders. By facilitating direct communication between the brain and external devices, BCIs have the potential to revolutionize neural activity monitoring, targeted neuromodulation strategies, and the restoration of brain functions. However, BCI technology faces significant challenges in achieving long-term, stable, high-quality recordings and accurately modulating neural activity. Traditional implantable electrodes, primarily made from rigid materials like metal, silicon, and carbon, provide excellent conductivity but encounter serious issues such as foreign body rejection, neural signal attenuation, and micromotion with brain tissue. To address these limitations, hydrogels are emerging as promising candidates for BCIs, given their mechanical and chemical similarities to brain tissues. These hydrogels are particularly suitable for implantable neural electrodes due to their three-dimensional water-rich structures, soft elastomeric properties, biocompatibility, and enhanced electrochemical characteristics. These exceptional features make them ideal for signal recording, neural modulation, and effective therapies for neurological conditions. This review highlights the current advancements in implantable hydrogel electrodes, focusing on their unique properties for neural signal recording and neuromodulation technologies, with the ultimate aim of treating brain disorders. A comprehensive overview is provided to encourage future progress in this field. Implantable hydrogel electrodes for BCIs have enormous potential to influence the broader scientific landscape and drive groundbreaking innovations across various sectors.},
}

@article {pmid40035293,
year = {2025},
author = {Schilling, KG and Grussu, F and Ianus, A and Hansen, B and Howard, AFD and Barrett, RLC and Aggarwal, M and Michielse, S and Nasrallah, F and Syeda, W and Wang, N and Veraart, J and Roebroeck, A and Bagdasarian, AF and Eichner, C and Sepehrband, F and Zimmermann, J and Soustelle, L and Bowman, C and Tendler, BC and Hertanu, A and Jeurissen, B and Verhoye, M and Frydman, L and van de Looij, Y and Hike, D and Dunn, JF and Miller, K and Landman, BA and Shemesh, N and Anderson, A and McKinnon, E and Farquharson, S and Dell'Acqua, F and Pierpaoli, C and Drobnjak, I and Leemans, A and Harkins, KD and Descoteaux, M and Xu, D and Huang, H and Santin, MD and Grant, SC and Obenaus, A and Kim, GS and Wu, D and Le Bihan, D and Blackband, SJ and Ciobanu, L and Fieremans, E and Bai, R and Leergaard, TB and Zhang, J and Dyrby, TB and Johnson, GA and Cohen-Adad, J and Budde, MD and Jelescu, IO},
title = {Considerations and recommendations from the ISMRM diffusion study group for preclinical diffusion MRI: Part 2-Ex vivo imaging: Added value and acquisition.},
journal = {Magnetic resonance in medicine},
volume = {},
number = {},
pages = {},
doi = {10.1002/mrm.30435},
pmid = {40035293},
issn = {1522-2594},
support = {202788/Z/16/A/WT_/Wellcome Trust/United Kingdom ; 203139/A/16/Z/WT_/Wellcome Trust/United Kingdom ; 203139/Z/16/Z/WT_/Wellcome Trust/United Kingdom ; K01EB032898/NH/NIH HHS/United States ; R01AG057991/NH/NIH HHS/United States ; R01CA160620/NH/NIH HHS/United States ; R01EB017230/NH/NIH HHS/United States ; R01EB019980/NH/NIH HHS/United States ; R01EB031765/NH/NIH HHS/United States ; R01EB031954/NH/NIH HHS/United States ; R01NS109090/NH/NIH HHS/United States ; R01NS125020/NH/NIH HHS/United States ; R56EB031765/NH/NIH HHS/United States ; },
abstract = {The value of preclinical diffusion MRI (dMRI) is substantial. While dMRI enables in vivo non-invasive characterization of tissue, ex vivo dMRI is increasingly being used to probe tissue microstructure and brain connectivity. Ex vivo dMRI has several experimental advantages including higher SNR and spatial resolution compared to in vivo studies, and enabling more advanced diffusion contrasts for improved microstructure and connectivity characterization. Another major advantage of ex vivo dMRI is the direct comparison with histological data, as a crucial methodological validation. However, there are a number of considerations that must be made when performing ex vivo experiments. The steps from tissue preparation, image acquisition and processing, and interpretation of results are complex, with many decisions that not only differ dramatically from in vivo imaging of small animals, but ultimately affect what questions can be answered using the data. This work represents "Part 2" of a three-part series of recommendations and considerations for preclinical dMRI. We describe best practices for dMRI of ex vivo tissue, with a focus on the value that ex vivo imaging adds to the field of dMRI and considerations in ex vivo image acquisition. We first give general considerations and foundational knowledge that must be considered when designing experiments. We briefly describe differences in specimens and models and discuss why some may be more or less appropriate for different studies. We then give guidelines for ex vivo protocols, including tissue fixation, sample preparation, and MR scanning. In each section, we attempt to provide guidelines and recommendations, but also highlight areas for which no guidelines exist (and why), and where future work should lie. An overarching goal herein is to enhance the rigor and reproducibility of ex vivo dMRI acquisitions and analyses, and thereby advance biomedical knowledge.},
}

@article {pmid40034942,
year = {2025},
author = {Tang, X and Fan, D and Wang, X and Xing, Z and Yu, S and Wang, A and Yu, H},
title = {Exploring how sensory dominance modulated by modality-specific expectation: an event-related potential study.},
journal = {Frontiers in psychology},
volume = {16},
number = {},
pages = {1548100},
pmid = {40034942},
issn = {1664-1078},
abstract = {The Colavita visual dominance effect refers to the phenomenon in which tend to respond only or preferentially to visual stimuli of bimodal audiovisual stimulus. Previous evidence has indicated that sensory dominance can be modulated by top-down expectation. However, it remains unclear how expectations directed toward a single sensory modality influence Colavita visual dominance at the electrophysiology level. Using event-related potential (ERP) measurements, we investigated how modality expectation modulates sensory dominance by manipulating the different unimodal target probabilities used in previous related Colavita studies. For the behavioral results, a significantly larger visual dominance effect was found when the modality expectation was directed to the visual sensory condition (40% V:10% A). Further ERPs results revealed that the mean amplitude of P2 (200-250 ms) in the central-parietal region was larger in the visual precedence auditory response (V_A) type than in the auditory precedence visual response (A_V) type when modality expectation was directed to visual sensory stimuli (40% V:10% A). In contrast, the mean amplitude of N2 (290-330 ms) in the frontal region was larger for the V_A type than in the A_V type when modality expectation was directed to the auditory sensory stimuli (10% V:40% A). Additionally, for the A_V type N1 (150-170 ms) in the frontal region was larger in visual versus auditory expectation condition. Overall, the study tentatively suggested that increasing unimodal target probability may lead to greater top-down expectation direct to target modality stimulus, and then sensory dominance emerges in the late phase when participant response to visual stimuli of bimodal audiovisual stimulus.},
}

@article {pmid40034836,
year = {2025},
author = {Alsuradi, H and Hong, J and Sarmadi, A and Volcic, R and Salam, H and Atashzar, SF and Khorrami, F and Eid, M},
title = {BandFocusNet: A Lightweight Model for Motor Imagery Classification of a Supernumerary Thumb in Virtual Reality.},
journal = {IEEE open journal of engineering in medicine and biology},
volume = {6},
number = {},
pages = {305-311},
pmid = {40034836},
issn = {2644-1276},
abstract = {Objective: Human movement augmentation through supernumerary effectors is an emerging field of research. However, controlling these effectors remains challenging due to issues with agency, control, and synchronizing movements with natural limbs. A promising control strategy for supernumerary effectors involves utilizing electroencephalography (EEG) through motor imagery (MI) functions. In this work, we investigate whether MI activity associated with a supernumerary effector could be reliably differentiated from that of a natural one, thus addressing the concern of concurrency. Twenty subjects were recruited to participate in a two-fold experiment in which they observed movements of natural and supernumerary thumbs, then engaged in MI of the observed movements, conducted in a virtual reality setting. Results: A lightweight deep-learning model that accounts for the temporal, spatial and spectral nature of the EEG data is proposed and called BandFocusNet, achieving an average classification accuracy of 70.9% using the leave-one-subject-out cross validation method. The trustworthiness of the model is examined through explainability analysis, and influential regions-of-interests are cross-validated through event-related-spectral-perturbation (ERSPs) analysis. Explainability results showed the importance of the right and left frontal cortical regions, and ERSPs analysis showed an increase in the delta and theta powers in these regions during the MI of the natural thumb but not during the MI of the supernumerary thumb. Conclusion: Evidence in the literature indicates that such activation is observed during the MI of natural effectors, and its absence could be interpreted as a lack of embodiment of the supernumerary thumb.},
}