Towards a mechanistic approach for the development of non-invasive brain-computer interfaces for motor rehabilitation

Development and evaluation of a BCI-neurofeedback system with real-time EEG detection and electrical stimulation assistance during motor attempt for neurorehabilitation of children with cerebral palsy

In the realm of motor rehabilitation, Brain-Computer Interface Neurofeedback Training (BCI-NFT) emerges as a promising strategy. This aims to utilize an individual's brain activity to stimulate or assist movement, thereby strengthening sensorimotor pathways and promoting motor recovery. Employing various methodologies, BCI-NFT has been shown to be effective for enhancing motor function primarily of the upper limb in stroke, with very few studies reported in cerebral palsy (CP). Our main objective was to develop an electroencephalography (EEG)-based BCI-NFT system, employing an associative learning paradigm, to improve selective control of ankle dorsiflexion in CP and potentially other neurological populations. First, in a cohort of eight healthy volunteers, we successfully implemented a BCI-NFT system based on detection of slow movement-related cortical potentials (MRCP) from EEG generated by attempted dorsiflexion to simultaneously activate Neuromuscular Electrical Stimulation which assisted movement and served to enhance sensory feedback to the sensorimotor cortex. Participants also viewed a computer display that provided real-time visual feedback of ankle range of motion with an individualized target region displayed to encourage maximal effort. After evaluating several potential strategies, we employed a Long short-term memory (LSTM) neural network, a deep learning algorithm, to detect the motor intent prior to movement onset. We then evaluated the system in a 10-session ankle dorsiflexion training protocol on a child with CP. By employing transfer learning across sessions, we could significantly reduce the number of calibration trials from 50 to 20 without compromising detection accuracy, which was 80.8% on average. The participant was able to complete the required calibration trials and the 100 training trials per session for all 10 sessions and post-training demonstrated increased ankle dorsiflexion velocity, walking speed and step length. Based on exceptional system performance, feasibility and preliminary effectiveness in a child with CP, we are now pursuing a clinical trial in a larger cohort of children with CP.

BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery

Brain-computer interfaces (BCIs) based on motor imagery (MI) enable the disabled to interact with the world through brain signals. To meet demands of real-time, stable, and diverse interactions, it is crucial to develop lightweight networks that can accurately and reliably decode multi-class MI tasks. In this paper, we introduce BrainGridNet, a convolutional neural network (CNN) framework that integrates two intersecting depthwise CNN branches with 3D electroencephalography (EEG) data to decode a five-class MI task. The BrainGridNet attains competitive results in both the time and frequency domains, with superior performance in the frequency domain. As a result, an accuracy of 80.26 percent and a kappa value of 0.753 are achieved by BrainGridNet, surpassing the state-of-the-art (SOTA) model. Additionally, BrainGridNet shows optimal computational efficiency, excels in decoding the most challenging subject, and maintains robust accuracy despite the random loss of 16 electrode signals. Finally, the visualizations demonstrate that BrainGridNet learns discriminative features and identifies critical brain regions and frequency bands corresponding to each MI class. The convergence of BrainGridNet's strong feature extraction capability, high decoding accuracy, steady decoding efficacy, and low computational costs renders it an appealing choice for facilitating the development of BCIs.

Advanced Electrode Technologies for Noninvasive Brain-Computer Interfaces

Brain-computer interfaces (BCIs) have garnered significant attention in recent years due to their potential applications in medical, assistive, and communication technologies. Building on this, noninvasive BCIs stand out as they provide a safe and user-friendly method for interacting with the human brain. In this work, we provide a comprehensive overview of the latest developments and advancements in material, design, and application of noninvasive BCIs electrode technology. We also explore the challenges and limitations currently faced by noninvasive BCI electrode technology and sketch out the technological roadmap from three dimensions: Materials and Design; Performances; Mode and Function. We aim to unite research efforts within the field of noninvasive BCI electrode technology, focusing on the consolidation of shared goals and fostering integrated development strategies among a diverse array of multidisciplinary researchers.

Evidence That Brain-Controlled Functional Electrical Stimulation Could Elicit Targeted Corticospinal Facilitation of Hand Muscles in Healthy Young Adults

OBJECTIVES

Brain-computer interface (BCI)-controlled functional electrical stimulation (FES) has been used in rehabilitation for improving hand motor function. However, mechanisms of improvements are still not well understood. The objective of this study was to investigate how BCI-controlled FES affects hand muscle corticospinal excitability.

MATERIALS AND METHODS

A total of 12 healthy young adults were recruited in the study. During BCI calibration, a single electroencephalography channel from the motor cortex and a frequency band were chosen to detect event-related desynchronization (ERD) of cortical oscillatory activity during kinesthetic wrist motor imagery (MI). The MI-based BCI system was used to detect active states on the basis of ERD activity in real time and produce contralateral wrist extension movements through FES of the extensor carpi radialis (ECR) muscle. As a control condition, FES was used to generate wrist extension at random intervals. The two interventions were performed on separate days and lasted 25 minutes. Motor evoked potentials (MEPs) in ECR (intervention target) and flexor carpi radialis (FCR) muscles were elicited through single-pulse transcranial magnetic stimulation of the motor cortex to compare corticospinal excitability before (pre), immediately after (post0), and 30 minutes after (post30) the interventions.

RESULTS

After the BCI-FES intervention, ECR muscle MEPs were significantly facilitated at post0 and post30 time points compared with before the intervention (pre), whereas there were no changes in the FCR muscle corticospinal excitability. Conversely, after the random FES intervention, both ECR and FCR muscle MEPs were unaffected compared with before the intervention (pre).

CONCLUSIONS

Our results demonstrated evidence that BCI-FES intervention could elicit muscle-specific short-term corticospinal excitability facilitation of the intervention targeted (ECR) muscle only, whereas randomly applied FES was ineffective in eliciting any changes. Notably, these findings suggest that associative cortical and peripheral activations during BCI-FES can effectively elicit targeted muscle corticospinal excitability facilitation, implying possible rehabilitation mechanisms.

Challenges of neural interfaces for stroke motor rehabilitation

More than 85% of stroke survivors suffer from different degrees of disability for the rest of their lives. They will require support that can vary from occasional to full time assistance. These conditions are also associated to an enormous economic impact for their families and health care systems. Current rehabilitation treatments have limited efficacy and their long-term effect is controversial. Here we review different challenges related to the design and development of neural interfaces for rehabilitative purposes. We analyze current bibliographic evidence of the effect of neuro-feedback in functional motor rehabilitation of stroke patients. We highlight the potential of these systems to reconnect brain and muscles. We also describe all aspects that should be taken into account to restore motor control. Our aim with this work is to help researchers designing interfaces that demonstrate and validate neuromodulation strategies to enforce a contingent and functional neural linkage between the central and the peripheral nervous system. We thus give clues to design systems that can improve or/and re-activate neuroplastic mechanisms and open a new recovery window for stroke patients.

Classification Algorithm for Electroencephalogram-based Motor Imagery Using Hybrid Neural Network with Spatio-temporal Convolution and Multi-head Attention Mechanism

Motor imagery (MI) is a brain-computer interface (BCI) technique in which specific brain regions are activated when people imagine their limbs (or muscles) moving, even without actual movement. The technology converts electroencephalogram (EEG) signals generated by the brain into computer-readable commands by measuring neural activity. Classification of motor imagery is one of the tasks in BCI. Researchers have done a lot of work on motor imagery classification, and the existing literature has relatively mature decoding methods for two-class motor tasks. However, as the categories of EEG-based motor imagery tasks increase, further exploration is needed for decoding research on four-class motor imagery tasks. In this study, we designed a hybrid neural network that combines spatiotemporal convolution and attention mechanisms. Specifically, the data is first processed by spatiotemporal convolution to extract features and then processed by a Multi-branch Convolution block. Finally, the processed data is input into the encoder layer of the Transformer for a self-attention calculation to obtain the classification results. Our approach was tested on the well-known MI datasets BCI Competition IV 2a and 2b, and the results show that the 2a dataset has a global average classification accuracy of 83.3% and a kappa value of 0.78. Experimental results show that the proposed method outperforms most of the existing methods.

Multi-Class Classification of Upper Limb Movements With Filter Bank Task-Related Component Analysis

The classification of limb movements can provide with control commands in non-invasive brain-computer interface. Previous studies on the classification of limb movements have focused on the classification of left/right limbs; however, the classification of different types of upper limb movements has often been ignored despite that it provides more active-evoked control commands in the brain-computer interface. Nevertheless, few machine learning method can be used as the state-of-the-art method in the multi-class classification of limb movements. This work focuses on the multi-class classification of upper limb movements and proposes the multi-class filter bank task-related component analysis (mFBTRCA) method, which consists of three steps: spatial filtering, similarity measuring and filter bank selection. The spatial filter, namely the task-related component analysis, is first used to remove noise from EEG signals. The canonical correlation measures the similarity of the spatial-filtered signals and is used for feature extraction. The correlation features are extracted from multiple low-frequency filter banks. The minimum-redundancy maximum-relevance selects the essential features from all the correlation features, and finally, the support vector machine is used to classify the selected features. The proposed method compared against previously used models is evaluated using two datasets. mFBTRCA achieved a classification accuracy of 0.4193 ± 0.0780 (7 classes) and 0.4032 ± 0.0714 (5 classes), respectively, which improves on the best accuracies achieved using the compared methods (0.3590 ± 0.0645 and 0.3159 ± 0.0736, respectively). The proposed method is expected to provide more control commands in the applications of non-invasive brain-computer interfaces.

Effects of neurofeedback training combined with transcranial direct current stimulation on motor imagery: A randomized controlled trial

Introduction

Neurofeedback (NFB) training and transcranial direct current stimulation (tDCS) have been shown to individually improve motor imagery (MI) abilities. However, the effect of combining both of them with MI has not been verified. Therefore, the aim of this study was to examine the effect of applying tDCS directly before MI with NFB.

Methods

Participants were divided into an NFB group (n = 10) that performed MI with NFB and an NFB + tDCS group (n = 10) that received tDCS for 10 min before MI with NFB. Both groups performed 60 MI trials with NFB. The MI task was performed 20 times without NFB before and after training, and μ-event-related desynchronization (ERD) and vividness MI were evaluated.

Results

μ-ERD increased significantly in the NFB + tDCS group compared to the NFB group. MI vividness significantly increased before and after training.

Discussion

Transcranial direct current stimulation and NFB modulate different processes with respect to MI ability improvement; hence, their combination might further improve MI performance. The results of this study indicate that the combination of NFB and tDCS for MI is more effective in improving MI abilities than applying them individually.

Beyond passive observation: feedback anticipation and observation activate the mirror system in virtual finger movement control via P300-BCI

Action observation (AO) is widely used as a post-stroke therapy to activate sensorimotor circuits through the mirror neuron system. However, passive observation is often considered to be less effective and less interactive than goal-directed movement observation, leading to the suggestion that observation of goal-directed actions may have stronger therapeutic potential, as goal-directed AO has been shown to activate mechanisms for monitoring action errors. Some studies have also suggested the use of AO as a form of Brain-computer interface (BCI) feedback. In this study, we investigated the potential for observation of virtual hand movements within a P300-based BCI as a feedback system to activate the mirror neuron system. We also explored the role of feedback anticipation and estimation mechanisms during movement observation. Twenty healthy subjects participated in the study. We analyzed event-related desynchronization and synchronization (ERD/S) of sensorimotor EEG rhythms and Error-related potentials (ErrPs) during observation of virtual hand finger flexion presented as feedback in the P300-BCI loop and compared the dynamics of ERD/S and ErrPs during observation of correct feedback and errors. We also analyzed these EEG markers during passive AO under two conditions: when subjects anticipated the action demonstration and when the action was unexpected. A pre-action mu-ERD was found both before passive AO and during action anticipation within the BCI loop. Furthermore, a significant increase in beta-ERS was found during AO within incorrect BCI feedback trials. We suggest that the BCI feedback may exaggerate the passive-AO effect, as it engages feedback anticipation and estimation mechanisms as well as movement error monitoring simultaneously. The results of this study provide insights into the potential of P300-BCI with AO-feedback as a tool for neurorehabilitation.

A Review of Brain Activity and EEG-Based Brain-Computer Interfaces for Rehabilitation Application

Patients with severe CNS injuries struggle primarily with their sensorimotor function and communication with the outside world. There is an urgent need for advanced neural rehabilitation and intelligent interaction technology to provide help for patients with nerve injuries. Recent studies have established the brain-computer interface (BCI) in order to provide patients with appropriate interaction methods or more intelligent rehabilitation training. This paper reviews the most recent research on brain-computer-interface-based non-invasive rehabilitation systems. Various endogenous and exogenous methods, advantages, limitations, and challenges are discussed and proposed. In addition, the paper discusses the communication between the various brain-computer interface modes used between severely paralyzed and locked patients and the surrounding environment, particularly the brain-computer interaction system utilizing exogenous (induced) EEG signals (such as P300 and SSVEP). This discussion reveals with an examination of the interface for collecting EEG signals, EEG components, and signal postprocessing. Furthermore, the paper describes the development of natural interaction strategies, with a focus on signal acquisition, data processing, pattern recognition algorithms, and control techniques.

Determining optimal mobile neurofeedback methods for motor neurorehabilitation in children and adults with non-progressive neurological disorders: a scoping review

Background

Brain–computer interfaces (BCI), initially designed to bypass the peripheral motor system to externally control movement using brain signals, are additionally being utilized for motor rehabilitation in stroke and other neurological disorders. Also called neurofeedback training, multiple approaches have been developed to link motor-related cortical signals to assistive robotic or electrical stimulation devices during active motor training with variable, but mostly positive, functional outcomes reported. Our specific research question for this scoping review was: for persons with non-progressive neurological injuries who have the potential to improve voluntary motor control, which mobile BCI-based neurofeedback methods demonstrate or are associated with improved motor outcomes for Neurorehabilitation applications?

Methods

We searched PubMed, Web of Science, and Scopus databases with all steps from study selection to data extraction performed independently by at least 2 individuals. Search terms included: brain machine or computer interfaces, neurofeedback and motor; however, only studies requiring a motor attempt, versus motor imagery, were retained. Data extraction included participant characteristics, study design details and motor outcomes.

Results

From 5109 papers, 139 full texts were reviewed with 23 unique studies identified. All utilized EEG and, except for one, were on the stroke population. The most commonly reported functional outcomes were the Fugl-Meyer Assessment (FMA; n = 13) and the Action Research Arm Test (ARAT; n = 6) which were then utilized to assess effectiveness, evaluate design features, and correlate with training doses. Statistically and functionally significant pre-to post training changes were seen in FMA, but not ARAT. Results did not differ between robotic and electrical stimulation feedback paradigms. Notably, FMA outcomes were positively correlated with training dose.

Conclusion

This review on BCI-based neurofeedback training confirms previous findings of effectiveness in improving motor outcomes with some evidence of enhanced neuroplasticity in adults with stroke. Associative learning paradigms have emerged more recently which may be particularly feasible and effective methods for Neurorehabilitation. More clinical trials in pediatric and adult neurorehabilitation to refine methods and doses and to compare to other evidence-based training strategies are warranted.

Poststroke motor, cognitive and speech rehabilitation with brain-computer interface: a perspective review

Brain-computer interface (BCI) technology translates brain activity into meaningful commands to establish a direct connection between the brain and the external world. Neuroscientific research in the past two decades has indicated a tremendous potential of BCI systems for the rehabilitation of patients suffering from poststroke impairments. By promoting the neuronal recovery of the damaged brain networks, BCI systems have achieved promising results for the recovery of poststroke motor, cognitive, and language impairments. Also, several assistive BCI systems that provide alternative means of communication and control to severely paralysed patients have been proposed to enhance patients' quality of life. In this article, we present a perspective review of the recent advances and challenges in the BCI systems used in the poststroke rehabilitation of motor, cognitive, and communication impairments.

Evaluation of Multi-layer Perceptron Neural Networks in Predicting Ankle Dorsiflexion in Healthy Adults using Movement-related Cortical Potentials for BCI-Neurofeedback Applications

Brain computer interface (BCI) systems were initially developed to replace lost function; however, they are being increasingly utilized in rehabilitation to restore motor functioning after brain injury. In such BCI-mediated neurofeedback training (BCI-NFT), the brain-state associated with movement attempt or intention is used to activate an external device which assists the movement while providing sensory feedback to enhance neuroplasticity. A critical element in the success of BCI-NFT is accurate timing of the feedback within the active period of the brain state. The overarching goal of this work was to develop a reliable deep learning model that can predict motion before its onset, and thereby deliver the sensory stimuli in a timely manner for BCI-NFT applications. To this end, the main objective of the current study was to design and evaluate a Multi-layer Perceptron Neural Network (MLP-NN). Movement-related cortical potentials (MRCP) during planning and execution of ankle dorsiflexion was used to train the model to classify dorsiflexion planning vs. rest. The accuracy and reliability of the model was evaluated offline using data from eight healthy individuals (age: 26.3 ± 7.6 years). First, we evaluated three different epoching strategies for defining our 2 classes, to identify the one which best discriminated rest from dorsiflexion. The best model accuracy for predicting ankle dorsiflexion from EEG before movement execution was 84.7%. Second, the effect of various spatial filters on the model accuracy was evaluated, demonstrating that the spatial filtering had minimal effect on model accuracy and reliability.

Design a novel BCI for neurorehabilitation using concurrent LFP and EEG features: a case study

Brain-computer interfaces (BCI) that enables people with severe motor disabilities to use their brain signals for direct control of objects have attracted increased interest in rehabilitation. To date, no study has investigated feasibility of the BCI framework incorporating both intracortical and scalp signals. Methods: Concurrent local field potential (LFP) from the hand-knob area and scalp EEG were recorded in a paraplegic patient undergoing a spike-based close-loop neurorehabilitation training. Based upon multimodal spatio-spectral feature extraction and Naive Bayes classification, we developed, for the first time, a novel LFP-EEG-BCI for motor intention decoding. A transfer learning (TL) approach was employed to further improve the feasibility. The performance of the proposed LFP-EEG-BCI for four-class upper-limb motor intention decoding was assessed. Results: Using a decision fusion strategy, we showed that the LFP-EEG-BCI significantly (p <0.05) outperformed single modal BCI (LFP-BCI and EEG-BCI) in terms of decoding accuracy with the best performance achieved using regularized common spatial pattern features. Interrogation of feature characteristics revealed discriminative spatial and spectral patterns, which may lead to new insights for better understanding of brain dynamics during different motor imagery tasks and promote development of efficient decoding algorithms. Moreover, we showed that similar classification performance could be obtained with few training trials, therefore highlighting the efficacy of TL. Conclusion: The present findings demonstrated the superiority of the novel LFP-EEG-BCI in motor intention decoding. Significance: This work introduced a novel LFP-EEG-BCI that may lead to new directions for developing practical neurorehabilitation systems with high detection accuracy and multi-paradigm feasibility in clinical applications.

Does feedback based on FES-evoked nociceptive withdrawal reflex condition event-related desynchronization? An exploratory study with brain-computer interfaces

Introduction.Event-related desynchronization (ERD) is used in brain-computer interfaces (BCI) to detect the user's motor intention (MI) and convert it into a command for an actuator to provide sensory feedback or mobility, for example by means of functional electrical stimulation (FES). Recent studies have proposed to evoke the nociceptive withdrawal reflex (NWR) using FES, in order to evoke synergistic movements of the lower limb and to facilitate the gait rehabilitation of stroke patients. The use of NWR to provide sensorimotor feedback in ERD-based BCI is novel; thererfore, the conditioning effect that nociceptive stimuli might have on MI is still unknown.Objetive.To assess the ERD produced during the MI after FES-evoked NWR, in order to evaluate if nociceptive stimuli condition subsequent ERDs.Methods. Data from 528 electroencephalography trials of 8 healthy volunteers were recorded and analyzed. Volunteers used an ERD-based BCI, which provided two types of feedback: intrisic by the FES-evoked NWR and extrinsic by virtual reality. The electromyogram of the tibialis anterior muscle was also recorded. The main outcome variables were the normalized root mean square of the evoked electromyogram (RMS_norm), the average electroencephalogram amplitude at the ERD frequency during MI (A¯MI) and the percentage decrease ofA¯MIrelative to rest (ERD%) at the first MI subsequent to the activation of the BCI.Results.No evidence of changes of theRMS_normon both theA¯MI(p = 0.663) and theERD%(p = 0.252) of the subsequent MI was detected. A main effect of the type of feedback was found in the subsequentA¯MI(p < 0.001), with intrinsic feedback resulting in a largerA¯MI.Conclusions.No evidence of ERD conditioning was observed using BCI feedback based on FES-evoked NWR .Significance.FES-evoked NWR could constitute a potential feedback modality in an ERD-based BCI to facilitate motor recovery of stroke people.

Challenges and Opportunities for the Future of Brain-Computer Interface in Neurorehabilitation

Brain-computer interfaces (BCIs) provide a unique technological solution to circumvent the damaged motor system. For neurorehabilitation, the BCI can be used to translate neural signals associated with movement intentions into tangible feedback for the patient, when they are unable to generate functional movement themselves. Clinical interest in BCI is growing rapidly, as it would facilitate rehabilitation to commence earlier following brain damage and provides options for patients who are unable to partake in traditional physical therapy. However, substantial challenges with existing BCI implementations have prevented its widespread adoption. Recent advances in knowledge and technology provide opportunities to facilitate a change, provided that researchers and clinicians using BCI agree on standardisation of guidelines for protocols and shared efforts to uncover mechanisms. We propose that addressing the speed and effectiveness of learning BCI control are priorities for the field, which may be improved by multimodal or multi-stage approaches harnessing more sensitive neuroimaging technologies in the early learning stages, before transitioning to more practical, mobile implementations. Clarification of the neural mechanisms that give rise to improvement in motor function is an essential next step towards justifying clinical use of BCI. In particular, quantifying the unknown contribution of non-motor mechanisms to motor recovery calls for more stringent control conditions in experimental work. Here we provide a contemporary viewpoint on the factors impeding the scalability of BCI. Further, we provide a future outlook for optimal design of the technology to best exploit its unique potential, and best practices for research and reporting of findings.