Aggregating intrinsic information to enhance BCI performance through federated learning.

Insufficient data is a long-standing challenge for Brain-Computer Interface (BCI) to build a high-performance deep learning model. Though numerous research groups and institutes collect a multitude of EEG datasets for the same BCI task, sharing EEG data from multiple sites is still challenging due to the heterogeneity of devices. The significance of this challenge cannot be overstated, given the critical role of data diversity in fostering model robustness. However, existing works rarely discuss this issue, predominantly centering their attention on model training within a single dataset, often in the context of inter-subject or inter-session settings. In this work, we propose a hierarchical personalized Federated Learning EEG decoding (FLEEG) framework to surmount this challenge. This innovative framework heralds a new learning paradigm for BCI, enabling datasets with disparate data formats to collaborate in the model training process. Each client is assigned a specific dataset and trains a hierarchical personalized model to manage diverse data formats and facilitate information exchange. Meanwhile, the server coordinates the training procedure to harness knowledge gleaned from all datasets, thus elevating overall performance. The framework has been evaluated in Motor Imagery (MI) classification with nine EEG datasets collected by different devices but implementing the same MI task. Results demonstrate that the proposed framework can boost classification performance up to 8.4% by enabling knowledge sharing between multiple datasets, especially for smaller datasets. Visualization results also indicate that the proposed framework can empower the local models to put a stable focus on task-related areas, yielding better performance. To the best of our knowledge, this is the first end-to-end solution to address this important challenge.

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain-computer interface.

Objective.Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients.Approach.We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients.Main results.Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects' data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p<0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p<0.001) and 5.55% (p<0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p>0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients.Significance.Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.

Score-Based Data Generation for EEG Spatial Covariance Matrices: Towards Boosting BCI Performance.

The efficacy of Electroencephalogram (EEG) classifiers can be augmented by increasing the quantity of available data. In the case of geometric deep learning classifiers, the input consists of spatial covariance matrices derived from EEGs. In order to synthesize these spatial covariance matrices and facilitate future improvements of geometric deep learning classifiers, we propose a generative modeling technique based on state-of-the-art score-based models. The quality of generated samples is evaluated through visual and quantitative assessments using a left/right-hand-movement motor imagery dataset. The exceptional pixel-level resolution of these generative samples highlights the formidable capacity of score-based generative modeling. Additionally, the center (Fréchet mean) of the generated samples aligns with neurophysiological evidence that event-related desynchronization and synchronization occur on electrodes C3 and C4 within the Mu and Beta frequency bands during motor imagery processing. The quantitative evaluation revealed that 84.3% of the generated samples could be accurately predicted by a pre-trained classifier and an improvement of up to 8.7% in the average accuracy over ten runs for a specific test subject in a holdout experiment.

Relevance-based channel selection in motor imagery brain-computer interface.

Objective.Channel selection in the electroencephalogram (EEG)-based brain-computer interface (BCI) has been extensively studied for over two decades, with the goal being to select optimal subject-specific channels that can enhance the overall decoding efficacy of the BCI. With the emergence of deep learning (DL)-based BCI models, there arises a need for fresh perspectives and novel techniques to conduct channel selection. In this regard, subject-independent channel selection is relevant, since DL models trained using cross-subject data offer superior performance, and the impact of inherent inter-subject variability of EEG characteristics on subject-independent DL training is not yet fully understood.Approach.Here, we propose a novel methodology for implementing subject-independent channel selection in DL-based motor imagery (MI)-BCI, using layer-wise relevance propagation (LRP) and neural network pruning. Experiments were conducted using Deep ConvNet and 62-channel MI data from the Korea University EEG dataset.Main Results.Using our proposed methodology, we achieved a 61% reduction in the number of channels without any significant drop (p = 0.09) in subject-independent classification accuracy, due to the selection of highly relevant channels by LRP. LRP relevance-based channel selections provide significantly better accuracies compared to conventional weight-based selections while using less than 40% of the total number of channels, with differences in accuracies ranging from 5.96% to 1.72%. The performance of the adapted sparse-LRP model using only 16% of the total number of channels is similar to that of the adapted baseline model (p = 0.13). Furthermore, the accuracy of the adapted sparse-LRP model using only 35% of the total number of channels exceeded that of the adapted baseline model by 0.53% (p = 0.81). Analyses of channels chosen by LRP confirm the neurophysiological plausibility of selection, and emphasize the influence of motor, parietal, and occipital channels in MI-EEG classification.Significance.The proposed method addresses a traditional issue in EEG-BCI decoding, while being relevant and applicable to the latest developments in the field of BCI. We believe that our work brings forth an interesting and important application of model interpretability as a problem-solving technique.

Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification.

Deep learning (DL) has been widely investigated in a vast majority of applications in electroencephalography (EEG)-based brain-computer interfaces (BCIs), especially for motor imagery (MI) classification in the past five years. The mainstream DL methodology for the MI-EEG classification exploits the temporospatial patterns of EEG signals using convolutional neural networks (CNNs), which have been particularly successful in visual images. However, since the statistical characteristics of visual images depart radically from EEG signals, a natural question arises whether an alternative network architecture exists apart from CNNs. To address this question, we propose a novel geometric DL (GDL) framework called Tensor-CSPNet, which characterizes spatial covariance matrices derived from EEG signals on symmetric positive definite (SPD) manifolds and fully captures the temporospatiofrequency patterns using existing deep neural networks on SPD manifolds, integrating with experiences from many successful MI-EEG classifiers to optimize the framework. In the experiments, Tensor-CSPNet attains or slightly outperforms the current state-of-the-art performance on the cross-validation and holdout scenarios in two commonly used MI-EEG datasets. Moreover, the visualization and interpretability analyses also exhibit the validity of Tensor-CSPNet for the MI-EEG classification. To conclude, in this study, we provide a feasible answer to the question by generalizing the DL methodologies on SPD manifolds, which indicates the start of a specific GDL methodology for the MI-EEG classification.

Generative Adversarial Networks-Based Data Augmentation for Brain-Computer Interface.

The performance of a classifier in a brain-computer interface (BCI) system is highly dependent on the quality and quantity of training data. Typically, the training data are collected in a laboratory where the users perform tasks in a controlled environment. However, users' attention may be diverted in real-life BCI applications and this may decrease the performance of the classifier. To improve the robustness of the classifier, additional data can be acquired in such conditions, but it is not practical to record electroencephalogram (EEG) data over several long calibration sessions. A potentially time- and cost-efficient solution is artificial data generation. Hence, in this study, we proposed a framework based on the deep convolutional generative adversarial networks (DCGANs) for generating artificial EEG to augment the training set in order to improve the performance of a BCI classifier. To make a comparative investigation, we designed a motor task experiment with diverted and focused attention conditions. We used an end-to-end deep convolutional neural network for classification between movement intention and rest using the data from 14 subjects. The results from the leave-one subject-out (LOO) classification yielded baseline accuracies of 73.04% for diverted attention and 80.09% for focused attention without data augmentation. Using the proposed DCGANs-based framework for augmentation, the results yielded a significant improvement of 7.32% for diverted attention ( ) and 5.45% for focused attention ( ). In addition, we implemented the method on the data set IVa from BCI competition III to distinguish different motor imagery tasks. The proposed method increased the accuracy by 3.57% ( ). This study shows that using GANs for EEG augmentation can significantly improve BCI performance, especially in real-life applications, whereby users' attention may be diverted.

A Multi-view CNN with Novel Variance Layer for Motor Imagery Brain Computer Interface.

Accurate and robust classification of Motor Imagery (MI) from Electroencephalography (EEG) signals is among the most challenging tasks in Brain-Computer Interface (BCI) field. To address this challenge, this paper proposes a novel, neuro-physiologically inspired convolutional neural network (CNN) named Filter-Bank Convolutional Network (FBCNet) for MI classification. Capturing neurophysiological signatures of MI, FBCNet first creates a multi-view representation of the data by bandpass-filtering the EEG into multiple frequency bands. Next, spatially discriminative patterns for each view are learned using a CNN layer. Finally, the temporal information is aggregated using a new variance layer and a fully connected layer classifies the resultant features into MI classes. We evaluate the performance of FBCNet on a publicly available dataset from Korea University for classification of left vs right hand MI in a subject-specific 10-fold cross-validation setting. Results show that FBCNet achieves more than 6.7% higher accuracy compared to other state-of-the-art deep learning architectures while requiring less than 1% of the learning parameters. We explain the higher classification accuracy achieved by FBCNet using feature visualization where we show the superiority of FBCNet in learning interpretable and highly generalizable discriminative features. We provide the source code of FBCNet for reproducibility of results.

Federated Transfer Learning for EEG Signal Classification.

The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets. Privacy concerns associated with EEG signals limit the possibility of constructing a large EEG-BCI dataset by the conglomeration of multiple small ones for jointly training machine learning models. Hence, in this paper, we propose a novel privacy-preserving DL architecture named federated transfer learning (FTL) for EEG classification that is based on the federated learning framework. Working with the single-trial covariance matrix, the proposed architecture extracts common discriminative information from multi-subject EEG data with the help of domain adaptation techniques. We evaluate the performance of the proposed architecture on the PhysioNet dataset for 2-class motor imagery classification. While avoiding the actual data sharing, our FTL approach achieves 2% higher classification accuracy in a subject-adaptive analysis. Also, in the absence of multi-subject data, our architecture provides 6% better accuracy compared to other state-of-the-art DL architectures.

BCI for stroke rehabilitation: motor and beyond.

Stroke is one of the leading causes of long-term disability among adults and contributes to major socio-economic burden globally. Stroke frequently results in multifaceted impairments including motor, cognitive and emotion deficits. In recent years, brain-computer interface (BCI)-based therapy has shown promising results for post-stroke motor rehabilitation. In spite of the success received by BCI-based interventions in the motor domain, non-motor impairments are yet to receive similar attention in research and clinical settings. Some preliminary encouraging results in post-stroke cognitive rehabilitation using BCI seem to suggest that it may also hold potential for treating non-motor deficits such as cognitive and emotion impairments. Moreover, past studies have shown an intricate relationship between motor, cognitive and emotion functions which might influence the overall post-stroke rehabilitation outcome. A number of studies highlight the inability of current treatment protocols to account for the implicit interplay between motor, cognitive and emotion functions. This indicates the necessity to explore an all-inclusive treatment plan targeting the synergistic influence of these standalone interventions. This approach may lead to better overall recovery than treating the individual deficits in isolation. In this paper, we review the recent advances in BCI-based post-stroke motor rehabilitation and highlight the potential for the use of BCI systems beyond the motor domain, in particular, in improving cognition and emotion of stroke patients. Building on the current results and findings of studies in individual domains, we next discuss the possibility of a holistic BCI system for motor, cognitive and affect rehabilitation which may synergistically promote restorative neuroplasticity. Such a system would provide an all-encompassing rehabilitation platform, leading to overarching clinical outcomes and transfer of these outcomes to a better quality of living. This is one of the first works to analyse the possibility of targeting cross-domain influence of post-stroke functional recovery enabled by BCI-based rehabilitation.

Assessment of the Efficacy of EEG-Based MI-BCI With Visual Feedback and EEG Correlates of Mental Fatigue for Upper-Limb Stroke Rehabilitation.

OBJECTIVE: This single-arm multisite trial investigates the efficacy of the neurostyle brain exercise therapy towards enhanced recovery (nBETTER) system, an electroencephalogram (EEG)-based motor imagery brain-computer interface (MI-BCI) employing visual feedback for upper-limb stroke rehabilitation, and the presence of EEG correlates of mental fatigue during BCI usage. METHODS: A total of 13 recruited stroke patients underwent thrice-weekly nBETTER therapy coupled with standard arm therapy over six weeks. Upper-extremity Fugl-Meyer motor assessment (FMA) scores were measured at baseline (week 0), post-intervention (week 6), and follow-ups (weeks 12 and 24). In total, 11/13 patients (mean age 55.2 years old, mean post-stroke duration 333.7 days, mean baseline FMA 35.5) completed the study. RESULTS: Significant FMA gains relative to baseline were observed at weeks 6 and 24. Retrospectively comparing to the standard arm therapy (SAT) control group and BCI with haptic knob (BCI-HK) intervention group from a previous similar study, the SAT group had no significant gains, whereas the BCI-HK group had significant gains at weeks 6, 12, and 24. EEG analysis revealed significant positive correlations between relative beta power and BCI performance in the frontal and central brain regions, suggesting that mental fatigue may contribute to poorer BCI performance. CONCLUSION: nBETTER, an EEG-based MI-BCI employing only visual feedback, helps stroke survivors sustain short-term FMA improvement. Analysis of EEG relative beta power indicates that mental fatigue may be present. SIGNIFICANCE: This study adds nBETTER to the growing literature of safe and effective stroke rehabilitation MI-BCI, and suggests an additional fatigue-monitoring role in future such BCI.

A Framework on Optimization Strategy for EEG Motor Imagery Recognition.

At present, in the process of encephalogram motor imagery decoding, facing the background of big data analysis, it has the necessity to design an effective system which is subject-independent. Pre-training is common to carry out before each experiment, which affects the practicability of the EEG system. In order to solve this problem, the most feasible method is to design a unified framework for deep learning optimization, which could capture the spatial and spectral dependence of original motor imagery EEG signals according to the features extracted by CNN and the temporal dependence extracted by RNN-LSTM. The framework is superimposed from both end-to-end and time-frequency domains so as to retain and learn interpretable motor imagery features. In addition, artificial EEG signals can be automatically generated by training the generated adversarial network, which can generate the feature distribution similar to the original EEG signals, increase the capacity of EEG samples, and ultimately improve the classification performance and robustness of EEG motor imagery recognition. This deep learning framework can improve the classification accuracy of motor imagery for different subjects. In addition, the network can learn from the original data with the least amount of preprocessing, thus eliminating the time-consuming data preparation process.

Effectiveness of a Personalized Brain-Computer Interface System for Cognitive Training in Healthy Elderly: A Randomized Controlled Trial.

BACKGROUND: Cognitive training has been demonstrated to improve cognitive performance in older adults. To date, no study has explored personalized training that targets the brain activity of each individual. OBJECTIVE: This is the first large-scale trial that examines the usefulness of personalized neurofeedback cognitive training. METHODS: We conducted a randomized-controlled trial with participants who were 60-80 years old, with Clinical Dementia Rating (CDR) score of 0-0.5, Mini-Mental State Examination (MMSE) score of 24 and above, and with no neuropsychiatric diagnosis. Participants were randomly assigned to the Intervention or Waitlist-Control group. The training system, BRAINMEM, has attention, working memory, and delayed recall game components. The intervention schedule comprised 24 sessions over eight weeks and three monthly booster sessions. The primary outcome was the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) total score after the 24-session training. RESULTS: There were no significant between-subjects differences in overall cognitive performance post-intervention. However, a sex moderation effect (p = 0.014) was present. Men in the intervention group performed better than those in the waitlist group (mean difference, +4.03 (95% CI 0.1 to 8.0), p = 0.046. Among females, however, both waitlist-control and intervention participants improved from baseline, although the between-group difference in improvement did not reach significance. BRAINMEM also received positive appraisal and intervention adherence from the participants. CONCLUSION: A personalized neurofeedback intervention is potentially feasible for use in cognitive training for older males. The sex moderation effect warrants further investigation and highlights the importance of taking sex into account during cognitive training.

Facilitating motor imagery-based brain-computer interface for stroke patients using passive movement.

Motor imagery-based brain-computer interface (MI-BCI) has been proposed as a rehabilitation tool to facilitate motor recovery in stroke. However, the calibration of a BCI system is a time-consuming and fatiguing process for stroke patients, which leaves reduced time for actual therapeutic interaction. Studies have shown that passive movement (PM) (i.e., the execution of a movement by an external agency without any voluntary motions) and motor imagery (MI) (i.e., the mental rehearsal of a movement without any activation of the muscles) induce similar EEG patterns over the motor cortex. Since performing PM is less fatiguing for the patients, this paper investigates the effectiveness of calibrating MI-BCIs from PM for stroke subjects in terms of classification accuracy. For this purpose, a new adaptive algorithm called filter bank data space adaptation (FB-DSA) is proposed. The FB-DSA algorithm linearly transforms the band-pass-filtered MI data such that the distribution difference between the MI and PM data is minimized. The effectiveness of the proposed algorithm is evaluated by an offline study on data collected from 16 healthy subjects and 6 stroke patients. The results show that the proposed FB-DSA algorithm significantly improved the classification accuracies of the PM and MI calibrated models (p < 0.05). According to the obtained classification accuracies, the PM calibrated models that were adapted using the proposed FB-DSA algorithm outperformed the MI calibrated models by an average of 2.3 and 4.5 % for the healthy and stroke subjects respectively. In addition, our results suggest that the disparity between MI and PM could be stronger in the stroke patients compared to the healthy subjects, and there would be thus an increased need to use the proposed FB-DSA algorithm in BCI-based stroke rehabilitation calibrated from PM.

Brain plasticity following MI-BCI training combined with tDCS in a randomized trial in chronic subcortical stroke subjects: a preliminary study.

Brain-computer interface-assisted motor imagery (MI-BCI) or transcranial direct current stimulation (tDCS) has been used in stroke rehabilitation, though their combinatory effect is unknown. We investigated brain plasticity following a combined MI-BCI and tDCS intervention in chronic subcortical stroke patients with unilateral upper limb disability. Nineteen patients were randomized into tDCS and sham-tDCS groups. Diffusion and perfusion MRI, and transcranial magnetic stimulation were used to study structural connectivity, cerebral blood flow (CBF), and corticospinal excitability, respectively, before and 4 weeks after the 2-week intervention. After quality control, thirteen subjects were included in the CBF analysis. Eleven healthy controls underwent 2 sessions of MRI for reproducibility study. Whereas motor performance showed comparable improvement, long-lasting neuroplasticity can only be detected in the tDCS group, where white matter integrity in the ipsilesional corticospinal tract and bilateral corpus callosum was increased but sensorimotor CBF was decreased, particularly in the ipsilesional side. CBF change in the bilateral parietal cortices also correlated with motor function improvement, consistent with the increased white matter integrity in the corpus callosum connecting these regions, suggesting an involvement of interhemispheric interaction. The preliminary results indicate that tDCS may facilitate neuroplasticity and suggest the potential for refining rehabilitation strategies for stroke patients.

A Unified Fisher's Ratio Learning Method for Spatial Filter Optimization.

To detect the mental task of interest, spatial filtering has been widely used to enhance the spatial resolution of electroencephalography (EEG). However, the effectiveness of spatial filtering is undermined due to the significant nonstationarity of EEG. Based on regularization, most of the conventional stationary spatial filter design methods address the nonstationarity at the cost of the interclass discrimination. Moreover, spatial filter optimization is inconsistent with feature extraction when EEG covariance matrices could not be jointly diagonalized due to the regularization. In this paper, we propose a novel framework for a spatial filter design. With Fisher's ratio in feature space directly used as the objective function, the spatial filter optimization is unified with feature extraction. Given its ratio form, the selection of the regularization parameter could be avoided. We evaluate the proposed method on a binary motor imagery data set of 16 subjects, who performed the calibration and test sessions on different days. The experimental results show that the proposed method yields improvement in classification performance for both single broadband and filter bank settings compared with conventional nonunified methods. We also provide a systematic attempt to compare different objective functions in modeling data nonstationarity with simulation studies.To detect the mental task of interest, spatial filtering has been widely used to enhance the spatial resolution of electroencephalography (EEG). However, the effectiveness of spatial filtering is undermined due to the significant nonstationarity of EEG. Based on regularization, most of the conventional stationary spatial filter design methods address the nonstationarity at the cost of the interclass discrimination. Moreover, spatial filter optimization is inconsistent with feature extraction when EEG covariance matrices could not be jointly diagonalized due to the regularization. In this paper, we propose a novel framework for a spatial filter design. With Fisher's ratio in feature space directly used as the objective function, the spatial filter optimization is unified with feature extraction. Given its ratio form, the selection of the regularization parameter could be avoided. We evaluate the proposed method on a binary motor imagery data set of 16 subjects, who performed the calibration and test sessions on different days. The experimental results show that the proposed method yields improvement in classification performance for both single broadband and filter bank settings compared with conventional nonunified methods. We also provide a systematic attempt to compare different objective functions in modeling data nonstationarity with simulation studies.

EEG-Based Strategies to Detect Motor Imagery for Control and Rehabilitation.

Advances in brain-computer interface (BCI) technology have facilitated the detection of Motor Imagery (MI) from electroencephalography (EEG). First, we present three strategies of using BCI to detect MI from EEG: operant conditioning that employed a fixed model, machine learning that employed a subject-specific model computed from calibration, and adaptive strategy that continuously compute the subject-specific model. Second, we review prevailing works that employed the operant conditioning and machine learning strategies. Third, we present our past work on six stroke patients who underwent a BCI rehabilitation clinical trial with averaged accuracies of 79.8% during calibration and 69.5% across 18 online feedback sessions. Finally, we perform an offline study in this paper on our work employing the adaptive strategy. The results yielded significant improvements of 12% (p < 0.001) and 9% (p < 0.001) using all the data and using limited preceding data respectively in the feedback accuracies. The results showed an increase in the amount of training data yielded improvements. Nevertheless, results of using limited preceding data showed a larger part of the improvement was due to the adaptive strategy and changing subject-specific models did not deteriorate the accuracies. Hence the adaptive strategy is effective in addressing the non-stationarity between calibration and feedback sessions.

Prediction and detection of seizures from simultaneous thalamic and scalp electroencephalography recordings.

OBJECTIVE The authors explored the feasibility of seizure detection and prediction using signals recorded from the anterior thalamic nucleus, a major target for deep brain stimulation (DBS) in the treatment of epilepsy. METHODS Using data from 5 patients (13 seizures in total), the authors performed a feasibility study and analyzed the performance of a seizure prediction and detection algorithm applied to simultaneously acquired scalp and thalamic electroencephalography (EEG). The thalamic signal was obtained from DBS electrodes. The applied algorithm used the similarity index as a nonlinear measure for seizure identification, with patient-specific channel and threshold selection. Receiver operating characteristic (ROC) curves were calculated using data from all patients and channels to compare the performance between DBS and EEG recordings. RESULTS Thalamic DBS recordings were associated with a mean prediction rate of 84%, detection rate of 97%, and false-alarm rate of 0.79/hr. In comparison, scalp EEG recordings were associated with a mean prediction rate of 71%, detection rate of 100%, and false-alarm rate of 1.01/hr. From the ROC curves, when considering all channels, DBS outperformed EEG for both detection and prediction of seizures. CONCLUSIONS This is the first study to compare automated seizure detection and prediction from simultaneous thalamic and scalp EEG recordings. The authors have demonstrated that signals recorded from DBS leads are more robust than EEG recordings and can be used to predict and detect seizures. These results indicate feasibility for future designs of closed-loop anterior nucleus DBS systems for the treatment of epilepsy.

Real-Time Subject-Independent Pattern Classification of Overt and Covert Movements from fNIRS Signals.

Recently, studies have reported the use of Near Infrared Spectroscopy (NIRS) for developing Brain-Computer Interface (BCI) by applying online pattern classification of brain states from subject-specific fNIRS signals. The purpose of the present study was to develop and test a real-time method for subject-specific and subject-independent classification of multi-channel fNIRS signals using support-vector machines (SVM), so as to determine its feasibility as an online neurofeedback system. Towards this goal, we used left versus right hand movement execution and movement imagery as study paradigms in a series of experiments. In the first two experiments, activations in the motor cortex during movement execution and movement imagery were used to develop subject-dependent models that obtained high classification accuracies thereby indicating the robustness of our classification method. In the third experiment, a generalized classifier-model was developed from the first two experimental data, which was then applied for subject-independent neurofeedback training. Application of this method in new participants showed mean classification accuracy of 63% for movement imagery tasks and 80% for movement execution tasks. These results, and their corresponding offline analysis reported in this study demonstrate that SVM based real-time subject-independent classification of fNIRS signals is feasible. This method has important applications in the field of hemodynamic BCIs, and neuro-rehabilitation where patients can be trained to learn spatio-temporal patterns of healthy brain activity.

Facilitating effects of transcranial direct current stimulation on motor imagery brain-computer interface with robotic feedback for stroke rehabilitation.

OBJECTIVE: To investigate the efficacy and effects of transcranial direct current stimulation (tDCS) on motor imagery brain-computer interface (MI-BCI) with robotic feedback for stroke rehabilitation. DESIGN: A sham-controlled, randomized controlled trial. SETTING: Patients recruited through a hospital stroke rehabilitation program. PARTICIPANTS: Subjects (N=19) who incurred a stroke 0.8 to 4.3 years prior, with moderate to severe upper extremity functional impairment, and passed BCI screening. INTERVENTIONS: Ten sessions of 20 minutes of tDCS or sham before 1 hour of MI-BCI with robotic feedback upper limb stroke rehabilitation for 2 weeks. Each rehabilitation session comprised 8 minutes of evaluation and 1 hour of therapy. MAIN OUTCOME MEASURES: Upper extremity Fugl-Meyer Motor Assessment (FMMA) scores measured end-intervention at week 2 and follow-up at week 4, online BCI accuracies from the evaluation part, and laterality coefficients of the electroencephalogram (EEG) from the therapy part of the 10 rehabilitation sessions. RESULTS: FMMA score improved in both groups at week 4, but no intergroup differences were found at any time points. Online accuracies of the evaluation part from the tDCS group were significantly higher than those from the sham group. The EEG laterality coefficients from the therapy part of the tDCS group were significantly higher than those of the sham group. CONCLUSIONS: The results suggest a role for tDCS in facilitating motor imagery in stroke.

A Randomized Controlled Trial of EEG-Based Motor Imagery Brain-Computer Interface Robotic Rehabilitation for Stroke.

Electroencephalography (EEG)-based motor imagery (MI) brain-computer interface (BCI) technology has the potential to restore motor function by inducing activity-dependent brain plasticity. The purpose of this study was to investigate the efficacy of an EEG-based MI BCI system coupled with MIT-Manus shoulder-elbow robotic feedback (BCI-Manus) for subjects with chronic stroke with upper-limb hemiparesis. In this single-blind, randomized trial, 26 hemiplegic subjects (Fugl-Meyer Assessment of Motor Recovery After Stroke [FMMA] score, 4-40; 16 men; mean age, 51.4 years; mean stroke duration, 297.4 days), prescreened with the ability to use the MI BCI, were randomly allocated to BCI-Manus or Manus therapy, lasting 18 hours over 4 weeks. Efficacy was measured using upper-extremity FMMA scores at weeks 0, 2, 4 and 12. ElEG data from subjects allocated to BCI-Manus were quantified using the revised brain symmetry index (rBSI) and analyzed for correlation with the improvements in FMMA score. Eleven and 15 subjects underwent BCI-Manus and Manus therapy, respectively. One subject in the Manus group dropped out. Mean total FMMA scores at weeks 0, 2, 4, and 12 weeks improved for both groups: 26.3±10.3, 27.4±12.0, 30.8±13.8, and 31.5±13.5 for BCI-Manus and 26.6±18.9, 29.9±20.6, 32.9±21.4, and 33.9±20.2 for Manus, with no intergroup differences (P=.51). More subjects attained further gains in FMMA scores at week 12 from BCI-Manus (7 of 11 [63.6%]) than Manus (5 of 14 [35.7%]). A negative correlation was found between the rBSI and FMMA score improvement (P=.044). BCI-Manus therapy was well tolerated and not associated with adverse events. In conclusion, BCI-Manus therapy is effective and safe for arm rehabilitation after severe poststroke hemiparesis. Motor gains were comparable to those attained with intensive robotic therapy (1,040 repetitions/session) despite reduced arm exercise repetitions using EEG-based MI-triggered robotic feedback (136 repetitions/session). The correlation of rBSI with motor improvements suggests that the rBSI can be used as a prognostic measure for BCI-based stroke rehabilitation.