Mapping and decoding cortical engagement during motor imagery, mental arithmetic, and silent word generation using MEG.

Accurate quantification of cortical engagement during mental imagery tasks remains a challenging brain-imaging problem with immediate relevance to developing brain-computer interfaces. We analyzed magnetoencephalography (MEG) data from 18 individuals completing cued motor imagery, mental arithmetic, and silent word generation tasks. Participants imagined movements of both hands (HANDS) and both feet (FEET), subtracted two numbers (SUB), and silently generated words (WORD). The task-related cortical engagement was inferred from beta band (17-25 Hz) power decrements estimated using a frequency-resolved beamforming method. In the hands and feet motor imagery tasks, beta power consistently decreased in premotor and motor areas. In the word and subtraction tasks, beta-power decrements showed engagements in language and arithmetic processing within the temporal, parietal, and inferior frontal regions. A support vector machine classification of beta power decrements yielded high accuracy rates of 74 and 68% for classifying motor-imagery (HANDS vs. FEET) and cognitive (WORD vs. SUB) tasks, respectively. From the motor-versus-nonmotor contrasts, excellent accuracy rates of 85 and 80% were observed for hands-versus-word and hands-versus-sub, respectively. A multivariate Gaussian-process classifier provided an accuracy rate of 60% for the four-way (HANDS-FEET-WORD-SUB) classification problem. Individual task performance was revealed by within-subject correlations of beta-decrements. Beta-power decrements are helpful metrics for mapping and decoding cortical engagement during mental processes in the absence of sensory stimuli or overt behavioral outputs. Markers derived based on beta decrements may be suitable for rehabilitation purposes, to characterize motor or cognitive impairments, or to treat patients recovering from a cerebral stroke.

Effects of maternal folic acid supplementation during the second and third trimesters of pregnancy on neurocognitive development in the child: an 11-year follow-up from a randomised controlled trial.

BACKGROUND: Maternal folic acid (FA) supplementation before and in early pregnancy prevents neural tube defects (NTD), but it is uncertain whether continuing FA after the first trimester has benefits on offspring health. We aimed to evaluate the effect of FA supplementation throughout pregnancy on cognitive performance and brain function in the child. METHODS: Follow-up investigation of 11-year-old children, residing in Northern Ireland, whose mothers had participated in a randomised trial of Folic Acid Supplementation in the Second and Third Trimesters (FASSTT) in pregnancy and received 400 µg/day FA or placebo from the 14th gestational week. Cognitive performance (Full Scale Intelligence Quotient, Verbal Comprehension, Working Memory, Perceptual Reasoning, and Processing Speed) was assessed using the Wechsler Intelligence Scale for Children. Neuronal function was assessed using magnetoencephalographic (MEG) brain imaging. RESULTS: Of 119 mother-child pairs in the FASSTT trial, 68 children were assessed for neurocognitive performance at 11-year follow-up (Dec 2017 to Nov 2018). Children of mothers randomised to FA compared with placebo scored significantly higher in two Processing Speed tests, i.e. symbol search (mean difference 2.9 points, 95% CI 0.3 to 5.5, p = 0.03) and cancellation (11.3 points, 2.5 to 20.1, p = 0.04), whereas the positive effect on Verbal Comprehension was significant in girls only (6.5 points, 1.2 to 11.8, p = 0.03). MEG assessment of neuronal responses to a language task showed increased power at the Beta (13-30 Hz, p = 0.01) and High Gamma (49-70 Hz, p = 0.04) bands in children from FA-supplemented mothers, suggesting more efficient semantic processing of language. CONCLUSIONS: Continued FA supplementation in pregnancy beyond the early period currently recommended to prevent NTD can benefit neurocognitive development of the child. MEG provides a non-invasive tool in paediatric research to objectively assess functional brain activity in response to nutrition and other interventions. TRIAL REGISTRATION: ISRCTN ISRCTN19917787 . Registered on 15 May 2013.

Detection of Mild Cognitive Impairment with MEG Functional Connectivity Using Wavelet-Based Neuromarkers.

Studies on developing effective neuromarkers based on magnetoencephalographic (MEG) signals have been drawing increasing attention in the neuroscience community. This study explores the idea of using source-based magnitude-squared spectral coherence as a spatial indicator for effective regions of interest (ROIs) localization, subsequently discriminating the participants with mild cognitive impairment (MCI) from a group of age-matched healthy control (HC) elderly participants. We found that the cortical regions could be divided into two distinctive groups based on their coherence indices. Compared to HC, some ROIs showed increased connectivity (hyper-connected ROIs) for MCI participants, whereas the remaining ROIs demonstrated reduced connectivity (hypo-connected ROIs). Based on these findings, a series of wavelet-based source-level neuromarkers for MCI detection are proposed and explored, with respect to the two distinctive ROI groups. It was found that the neuromarkers extracted from the hyper-connected ROIs performed significantly better for MCI detection than those from the hypo-connected ROIs. The neuromarkers were classified using support vector machine (SVM) and k-NN classifiers and evaluated through Monte Carlo cross-validation. An average recognition rate of 93.83% was obtained using source-reconstructed signals from the hyper-connected ROI group. To better conform to clinical practice settings, a leave-one-out cross-validation (LOOCV) approach was also employed to ensure that the data for testing was from a participant that the classifier has never seen. Using LOOCV, we found the best average classification accuracy was reduced to 83.80% using the same set of neuromarkers obtained from the ROI group with functional hyper-connections. This performance surpassed the results reported using wavelet-based features by approximately 15%. Overall, our work suggests that (1) certain ROIs are particularly effective for MCI detection, especially when multi-resolution wavelet biomarkers are employed for such diagnosis; (2) there exists a significant performance difference in system evaluation between research-based experimental design and clinically accepted evaluation standards.

Covariate shift estimation based adaptive ensemble learning for handling non-stationarity in motor imagery related EEG-based brain-computer interface.

The non-stationary nature of electroencephalography (EEG) signals makes an EEG-based brain-computer interface (BCI) a dynamic system, thus improving its performance is a challenging task. In addition, it is well-known that due to non-stationarity based covariate shifts, the input data distributions of EEG-based BCI systems change during inter- and intra-session transitions, which poses great difficulty for developments of online adaptive data-driven systems. Ensemble learning approaches have been used previously to tackle this challenge. However, passive scheme based implementation leads to poor efficiency while increasing high computational cost. This paper presents a novel integration of covariate shift estimation and unsupervised adaptive ensemble learning (CSE-UAEL) to tackle non-stationarity in motor-imagery (MI) related EEG classification. The proposed method first employs an exponentially weighted moving average model to detect the covariate shifts in the common spatial pattern features extracted from MI related brain responses. Then, a classifier ensemble was created and updated over time to account for changes in streaming input data distribution wherein new classifiers are added to the ensemble in accordance with estimated shifts. Furthermore, using two publicly available BCI-related EEG datasets, the proposed method was extensively compared with the state-of-the-art single-classifier based passive scheme, single-classifier based active scheme and ensemble based passive schemes. The experimental results show that the proposed active scheme based ensemble learning algorithm significantly enhances the BCI performance in MI classifications.

A practical computerized decision support system for predicting the severity of Alzheimer's disease of an individual.

Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R 2 = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we then designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.

Robust EEG/MEG Based Functional Connectivity with the Envelope of the Imaginary Coherence: Sensor Space Analysis.

The brain's functional connectivity (FC) estimated at sensor level from electromagnetic (EEG/MEG) signals can provide quick and useful information towards understanding cognition and brain disorders. Volume conduction (VC) is a fundamental issue in FC analysis due to the effects of instantaneous correlations. FC methods based on the imaginary part of the coherence (iCOH) of any two signals are readily robust to VC effects, but neglecting the real part of the coherence leads to negligible FC when the processes are truly connected but with zero or π-phase (modulus 2π) interaction. We ameliorate this issue by proposing a novel method that implements an envelope of the imaginary coherence (EIC) to approximate the coherence estimate of supposedly active underlying sources. We compare EIC with state-of-the-art FC measures that included lagged coherence, iCOH, phase lag index (PLI) and weighted PLI (wPLI), using bivariate autoregressive and stochastic neural mass models. Additionally, we create realistic simulations where three and five regions were mapped on a template cortical surface and synthetic MEG signals were obtained after computing the electromagnetic leadfield. With this simulation and comparison study, we also demonstrate the feasibility of sensor FC analysis using receiver operating curve analysis whilst varying the signal's noise level. However, these results should be interpreted with caution given the known limitations of the sensor-based FC approach. Overall, we found that EIC and iCOH demonstrate superior results with most accurate FC maps. As they complement each other in different scenarios, that will be important to study normal and diseased brain activity.

Signal Propagation in the Human Visual Pathways: An Effective Connectivity Analysis.

Although the visual system has been extensively investigated, an integrated account of the spatiotemporal dynamics of long-range signal propagation along the human visual pathways is not completely known or validated. In this work, we used dynamic causal modeling approach to provide insights into the underlying neural circuit dynamics of pattern reversal visual-evoked potentials extracted from concurrent EEG-fMRI data. A recurrent forward-backward connectivity model, consisting of multiple interacting brain regions identified by EEG source localization aided by fMRI spatial priors, best accounted for the data dynamics. Sources were first identified in the thalamic area, primary visual cortex, as well as higher cortical areas along the ventral and dorsal visual processing streams. Consistent with hierarchical early visual processing, the model disclosed and quantified the neural temporal dynamics across the identified activity sources. This signal propagation is dominated by a feedforward process, but we also found weaker effective feedback connectivity. Using effective connectivity analysis, the optimal dynamic causal modeling revealed enhanced connectivity along the dorsal pathway but slightly suppressed connectivity along the ventral pathway. A bias was also found in favor of the right hemisphere consistent with functional attentional asymmetry. This study validates, for the first time, the long-range signal propagation timing in the human visual pathways. A similar modeling approach can potentially be used to understand other cognitive processes and dysfunctions in signal propagation in neurological and neuropsychiatric disorders. Significance statement: An integrated account of long-range visual signal propagation in the human brain is currently incomplete. Using computational neural modeling on our acquired concurrent EEG-fMRI data under a visual evoked task, we found not only a substantial forward propagation toward "higher-order" brain regions but also a weaker backward propagation. Asymmetry in our model's long-range connectivity accounted for the various observed activity biases. Importantly, the model disclosed the timing of signal propagation across these connectivity pathways and validates, for the first time, long-range signal propagation in the human visual system. A similar modeling approach could be used to identify neural pathways for other cognitive processes and their dysfunctions in brain disorders.

On self-feedback connectivity in neural mass models applied to event-related potentials.

Neural mass models (NMMs) applied to neuroimaging data often do not emphasise intrinsic self-feedback within a neural population. However, based on mean-field theory, any population of coupled neurons is intrinsically endowed with effective self-coupling. In this work, we examine the effectiveness of three cortical NMMs with different self-feedbacks using a dynamic causal modelling approach. Specifically, we compare the classic Jansen and Rit (1995) model (no self-feedback), a modified model by Moran et al. (2007) (only inhibitory self-feedback), and our proposed model with inhibitory and excitatory self-feedbacks. Using bifurcation analysis, we show that single-unit Jansen-Rit model is less robust in generating oscillatory behaviour than the other two models. Next, under Bayesian inversion, we simulate single-channel event-related potentials (ERPs) within a mismatch negativity auditory oddball paradigm. We found fully self-feedback model (FSM) to provide the best fit to single-channel data. By analysing the posterior covariances of model parameters, we show that self-feedback connections are less sensitive to the generated evoked responses than the other model parameters, and hence can be treated analogously to "higher-order" parameter corrections of the original Jansen-Rit model. This is further supported in the more realistic multi-area case where FSM can replicate data better than JRM and MoM in the majority of subjects by capturing the finer features of the ERP data more accurately. Our work informs how NMMs with full self-feedback connectivity are not only more consistent with the underlying neurophysiology, but can also account for more complex features in ERP data.

Electrophysiological signatures of intentional social coordination in the 10-12 Hz range.

This study sought to investigate the effects of manipulating social coordination on brain synchronization/de-synchronization in the mu band. Mu activation is associated with understanding and coordinating motor acts and may play a key role in mediating social interaction. Members of a dyad were required to interact with one another in a rhythmic finger movement coordination task under various instructions: intrinsic where each member of the dyad was instructed to maintain their own and ignore their partner's movement; in-phase where they were asked to synchronize with their partner's movement; and anti-phase where they were instructed to syncopate with their partner's movement. EEG and movement data were recorded simultaneously from both subjects during all three tasks and a control condition. Log power ratios of EEG activity in the active conditions versus control were used to assess the effect of task context on synchronization/de-synchronization in the mu spectral domain. Results showed clear and systematic modulation of mu band activity in the 10-12 Hz range as a function of coordination context. In the left hemisphere general levels of alpha-mu suppression increased progressively as one moved from intrinsic through in-phase to anti-phase contexts but with no specific central-parietal focus. In contrast the right hemisphere displayed context-specific changes in the central-parietal region. The intrinsic condition showed a right synchronization which disappeared with the in-phase context even as de-synchronization remained greater in the left hemisphere. Anti-phase was associated with larger mu suppression in the right in comparison with left at central-parietal region. Such asymmetrical changes were highly correlated with changing behavioral dynamics. These specific patterns of activation and deactivation of mu activity suggest that localized neural circuitry in right central-parietal regions mediates how individuals interpret the movements of others in the context of their own actions. A right sided mechanism in the 10-12 Hz range appears to be involved in integrating the mutual information among the members of a dyad that enables the dynamics of social interaction to unfold in time.

Alzheimer's Disease Assessments Optimized for Diagnostic Accuracy and Administration Time.

OBJECTIVE: Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the time taken to administer diagnostic assessment has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer's disease diagnosis. METHODS: We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open-source dementia dataset. We use cost-sensitive feature selection to optimise our feature selection results for assessment time as well as diagnostic accuracy. To encourage clinical adoption and further evaluation of our proposed accuracy-vs-cost optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items. RESULTS: We find that there are subsets of accuracy-cost optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments. DISCUSSION: Overall, our analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments. Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.

Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis.

Accurate computational models for clinical decision support systems require clean and reliable data but, in clinical practice, data are often incomplete. Hence, missing data could arise not only from training datasets but also test datasets which could consist of a single undiagnosed case, an individual. This work addresses the problem of extreme missingness in both training and test data by evaluating multiple imputation and classification workflows based on both diagnostic classification accuracy and computational cost. Extreme missingness is defined as having ∼50% of the total data missing in more than half the data features. In particular, we focus on dementia diagnosis due to long time delays, high variability, high attrition rates and lack of practical data imputation strategies in its diagnostic pathway. We identified and replicated the extreme missingness structure of data from a real-world memory clinic on a larger open dataset, with the original complete data acting as ground truth. Overall, we found that computational cost, but not accuracy, varies widely for various imputation and classification approaches. Particularly, we found that iterative imputation on the training dataset combined with a reduced-feature classification model provides the best approach, in terms of speed and accuracy. Taken together, this work has elucidated important factors to be considered when developing a predictive model for a dementia diagnostic support system.

Multiple Cost Optimisation for Alzheimer's Disease Diagnosis.

Current machine learning techniques for dementia diagnosis often do not take into account real-world practical constraints, which may include, for example, the cost of diagnostic assessment time and financial budgets. In this work, we built on previous cost-sensitive feature selection approaches by generalising to multiple cost types, while taking into consideration that stakeholders attempting to optimise the dementia care pathway might face multiple non-fungible budget constraints. Our new optimisation algorithm involved the searching of cost-weighting hyperparameters while constrained by total budgets. We then provided a proof of concept using both assessment time cost and financial budget cost. We showed that budget constraints could control the feature selection process in an intuitive and practical manner, while adjusting the hyperparameter increased the range of solutions selected by feature selection. We further showed that our budget-constrained cost optimisation framework could be implemented in a user-friendly graphical user interface sandbox tool to encourage non-technical users and stakeholders to adopt and to further explore and audit the model - a humans-in-the-loop approach. Overall, we suggest that setting budget constraints initially and then fine tuning the cost-weighting hyperparameters can be an effective way to perform feature selection where multiple cost constraints exist, which will in turn lead to more realistic optimising and redesigning of dementia diagnostic assessments. Clinical Relevance-By optimising diagnostic accuracy against various costs (e.g. assessment administration time and financial budget) predictive yet practical dementia diagnostic assessments can be redesigned to suit clinical use.

A magnetoencephalography dataset for motor and cognitive imagery-based brain-computer interface.

Recent advancements in magnetoencephalography (MEG)-based brain-computer interfaces (BCIs) have shown great potential. However, the performance of current MEG-BCI systems is still inadequate and one of the main reasons for this is the unavailability of open-source MEG-BCI datasets. MEG systems are expensive and hence MEG datasets are not readily available for researchers to develop effective and efficient BCI-related signal processing algorithms. In this work, we release a 306-channel MEG-BCI data recorded at 1KHz sampling frequency during four mental imagery tasks (i.e. hand imagery, feet imagery, subtraction imagery, and word generation imagery). The dataset contains two sessions of MEG recordings performed on separate days from 17 healthy participants using a typical BCI imagery paradigm. The current dataset will be the only publicly available MEG imagery BCI dataset as per our knowledge. The dataset can be used by the scientific community towards the development of novel pattern recognition machine learning methods to detect brain activities related to motor imagery and cognitive imagery tasks using MEG signals.

Integrated space-frequency-time domain feature extraction for MEG-based Alzheimer's disease classification.

Magnetoencephalography (MEG) has been combined with machine learning techniques, to recognize the Alzheimer's disease (AD), one of the most common forms of dementia. However, most of the previous studies are limited to binary classification and do not fully utilize the two available MEG modalities (extracted using magnetometer and gradiometer sensors). AD consists of several stages of progression, this study addresses this limitation by using both magnetometer and gradiometer data to discriminate between participants with AD, AD-related mild cognitive impairment (MCI), and healthy control (HC) participants in the form of a three-class classification problem. A series of wavelet-based biomarkers are developed and evaluated, which concurrently leverage the spatial, frequency and time domain characteristics of the signal. A bimodal recognition system based on an improved score-level fusion approach is proposed to reinforce interpretation of the brain activity captured by magnetometers and gradiometers. In this preliminary study, it was found that the markers derived from gradiometer tend to outperform the magnetometer-based markers. Interestingly, out of the total 10 regions of interest, left-frontal lobe demonstrates about 8% higher mean recognition rate than the second-best performing region (left temporal lobe) for AD/MCI/HC classification. Among the four types of markers proposed in this work, the spatial marker developed using wavelet coefficients provided the best recognition performance for the three-way classification. Overall, the proposed approach provides promising results for the potential of AD/MCI/HC three-way classification utilizing the bimodal MEG data.

High-dimensional brain-wide functional connectivity mapping in magnetoencephalography.

BACKGROUND: Brain functional connectivity (FC) analyses based on magneto/electroencephalography (M/EEG) signals have yet to exploit the intrinsic high-dimensional information. Typically, these analyses are constrained to regions of interest to avoid the curse of dimensionality, with the latter leading to conservative hypothesis testing. NEW METHOD: We removed such constraint by estimating high-dimensional source-based M/EEG-FC using cluster-permutation statistic (CPS) and demonstrated the feasibility of this approach by identifying resting-state changes in mild cognitive impairment (MCI), a prodromal stage of Alzheimer's disease. Particularly, we proposed a unified framework for CPS analysis together with a novel neighbourhood measure to estimate more compact and neurophysiological plausible neural communication. As clusters could more confidently reveal interregional communication, we proposed and tested a cluster-strength index to demonstrate other advantages of CPS analysis. RESULTS: We found clusters of increased communication or hypersynchronization in MCI compared to healthy controls in delta (1-4 Hz) and higher-theta (6-8 Hz) bands oscillations. These mainly consisted of interactions between occipitofrontal and occipitotemporal regions in the left hemisphere, which may be critically affected in the early stages of Alzheimer's disease. CONCLUSIONS: Our approach could be important to create high-resolution FC maps from neuroimaging studies in general, allowing the multimodal analysis of neural communication across multiple spatial scales. Particularly, FC clusters more robustly represent the interregional communication by identifying dense bundles of connections that are less sensitive to inter-individual anatomical and functional variability. Overall, this approach could help to better understand neural information processing in healthy and disease conditions as needed for developing biomarker research.

An Early Stage Researcher's Primer on Systems Medicine Terminology.

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.

Applying a brain-computer interface to support motor imagery practice in people with stroke for upper limb recovery: a feasibility study.

BACKGROUND: There is now sufficient evidence that using a rehabilitation protocol involving motor imagery (MI) practice in conjunction with physical practice (PP) of goal-directed rehabilitation tasks leads to enhanced functional recovery of paralyzed limbs among stroke sufferers. It is however difficult to confirm patient engagement during an MI in the absence of any on-line measure. Fortunately an EEG-based brain-computer interface (BCI) can provide an on-line measure of MI activity as a neurofeedback for the BCI user to help him/her focus better on the MI task. However initial performance of novice BCI users may be quite moderate and may cause frustration. This paper reports a pilot study in which a BCI system is used to provide a computer game-based neurofeedback to stroke participants during the MI part of a protocol. METHODS: The participants included five chronic hemiplegic stroke sufferers. Participants received up to twelve 30-minute MI practice sessions (in conjunction with PP sessions of the same duration) on 2 days a week for 6 weeks. The BCI neurofeedback performance was evaluated based on the MI task classification accuracy (CA) rate. A set of outcome measures including action research arm test (ARAT) and grip strength (GS), was made use of in assessing the upper limb functional recovery. In addition, since stroke sufferers often experience physical tiredness, which may influence the protocol effectiveness, their fatigue and mood levels were assessed regularly. RESULTS: Positive improvement in at least one of the outcome measures was observed in all the participants, while improvements approached a minimal clinically important difference (MCID) for the ARAT. The on-line CA of MI induced sensorimotor rhythm (SMR) modulation patterns in the form of lateralized event-related desynchronization (ERD) and event-related synchronization (ERS) effects, for novice participants was in a moderate range of 60-75% within the limited 12 training sessions. The ERD/ERS change from the first to the last session was statistically significant for only two participants. CONCLUSIONS: Overall the crucial observation is that the moderate BCI classification performance did not impede the positive rehabilitation trends as quantified with the rehabilitation outcome measures adopted in this study. Therefore it can be concluded that the BCI supported MI is a feasible intervention as part of a post-stroke rehabilitation protocol combining both PP and MI practice of rehabilitation tasks. Although these findings are promising, the scope of the final conclusions is limited by the small sample size and the lack of a control group.

Deep Learning Based Inter-subject Continuous Decoding of Motor Imagery for Practical Brain-Computer Interfaces.

Inter-subject transfer learning is a long-standing problem in brain-computer interfaces (BCIs) and has not yet been fully realized due to high inter-subject variability in the brain signals related to motor imagery (MI). The recent success of deep learning-based algorithms in classifying different brain signals warrants further exploration to determine whether it is feasible for the inter-subject continuous decoding of MI signals to provide contingent neurofeedback which is important for neurorehabilitative BCI designs. In this paper, we have shown how a convolutional neural network (CNN) based deep learning framework can be used for inter-subject continuous decoding of MI related electroencephalographic (EEG) signals using the novel concept of Mega Blocks for adapting the network against inter-subject variabilities. These Mega Blocks have the capacity to repeat a specific architectural block several times such as one or more convolutional layers in a single Mega Block. The parameters of such Mega Blocks can be optimized using Bayesian hyperparameter optimization. The results, obtained on the publicly available BCI competition IV-2b dataset, yields an average inter-subject continuous decoding accuracy of 71.49% (κ = 0.42) and 70.84% (κ = 0.42) for two different training methods such as adaptive moment estimation (Adam) and stochastic gradient descent (SGDM), respectively, in 7 out of 9 subjects. Our results show for the first time that it is feasible to use CNN based architectures for inter-subject continuous decoding with a sufficient level of accuracy for developing calibration-free MI-BCIs for practical purposes.

Assessing impact of channel selection on decoding of motor and cognitive imagery from MEG data.

OBJECTIVE: Magnetoencephalography (MEG) based brain-computer interface (BCI) involves a large number of sensors allowing better spatiotemporal resolution for assessing brain activity patterns. There have been many efforts to develop BCI using MEG with high accuracy, though an increase in the number of channels (NoC) means an increase in computational complexity. However, not all sensors necessarily contribute significantly to an increase in classification accuracy (CA) and specifically in the case of MEG-based BCI no channel selection methodology has been performed. Therefore, this study investigates the effect of channel selection on the performance of MEG-based BCI. APPROACH: MEG data were recorded for two sessions from 15 healthy participants performing motor imagery, cognitive imagery and a mixed imagery task pair using a unique paradigm. Performance of four state-of-the-art channel selection methods (i.e. Class-Correlation, ReliefF, Random Forest, and Infinite Latent Feature Selection were applied across six binary tasks in three different frequency bands) were evaluated in this study on two state-of-the-art features, i.e. bandpower and common spatial pattern (CSP). MAIN RESULTS: All four methods provided a statistically significant increase in CA compared to a baseline method using all gradiometer sensors, i.e. 204 channels with band-power features from alpha (8-12 Hz), beta (13-30 Hz), or broadband (α + ß) (8-30 Hz). It is also observed that the alpha frequency band performed better than the beta and broadband frequency bands. The performance of the beta band gave the lowest CA compared with the other two bands. Channel selection improved accuracy irrespective of feature types. Moreover, all the methods reduced the NoC significantly, from 204 to a range of 1-25, using bandpower as a feature and from 15 to 105 for CSP. The optimal channel number also varied not only in each session but also for each participant. Reducing the NoC will help to decrease the computational cost and maintain numerical stability in cases of low trial numbers. SIGNIFICANCE: The study showed significant improvement in performance of MEG-BCI with channel selection irrespective of feature type and hence can be successfully applied for BCI applications.

Tangent Space Features-Based Transfer Learning Classification Model for Two-Class Motor Imagery Brain-Computer Interface.

The performance of a brain-computer interface (BCI) will generally improve by increasing the volume of training data on which it is trained. However, a classifier's generalization ability is often negatively affected when highly non-stationary data are collected across both sessions and subjects. The aim of this work is to reduce the long calibration time in BCI systems by proposing a transfer learning model which can be used for evaluating unseen single trials for a subject without the need for training session data. A method is proposed which combines a generalization of the previously proposed subject-specific "multivariate empirical-mode decomposition" preprocessing technique by taking a fixed band of 8-30Hz for all four motor imagery tasks and a novel classification model which exploits the structure of tangent space features drawn from the Riemannian geometry framework, that is shared among the training data of multiple sessions and subjects. Results demonstrate comparable performance improvement across multiple subjects without subject-specific calibration, when compared with other state-of-the-art techniques.