Robotic orthosis compared to virtual hand for Brain–Computer Interface feedback

Adaptive filter of frequency bands based coordinate attention network for EEG-based motor imagery classification

Purpose

In the brain-computer interface (BCI), motor imagery (MI) could be defined as the Electroencephalogram (EEG) signals through imagined movements, and ultimately enabling individuals to control external devices. However, the low signal-to-noise ratio, multiple channels and non-linearity are the essential challenges of accurate MI classification. To tackle these issues, we investigate the role of adaptive frequency bands selection and spatial-temporal feature learning in decoding motor imagery.

Methods

We propose an Adaptive Filter of Frequency Bands based Coordinate Attention Network (AFFB-CAN) to improve the performance of MI classification. Specifically, we design the AFFB to adaptively obtain the upper and lower limits of frequency bands in order to alleviate information loss caused by manual selection. Next, we propose the CAN-based network to emphasize the key brain regions and temporal segments. And we design a multi-scale module to enhance temporal context learning.

Results

The conducted experiments on the BCI Competition IV-2a and 2b datasets reveal that our approach achieves an outstanding average accuracy, kappa values, and Macro F1-Score with 0.7825, 0.7104, and 0.7486 respectively. Similarly, for the BCI Competition IV-2b dataset, the average accuracy, kappa values, and F1-Score obtained are 0.8879, 0.7427, and 0.8734, respectively.

Conclusion

The proposed AFFB-CAN method improves the performance of MI classification. In addition, our study confirms previous findings that motor imagery is mainly associated with µ and β rhythms. Moreover, we also find that γ rhythms also play an important role in MI classification.

Brain-computer interface in critical care and rehabilitation

This comprehensive review explores the broad landscape of brain-computer interface (BCI) technology and its potential use in intensive care units (ICUs), particularly for patients with motor impairments such as quadriplegia or severe brain injury. By employing brain signals from various sensing techniques, BCIs offer enhanced communication and motor rehabilitation strategies for patients. This review underscores the concept and efficacy of noninvasive, electroencephalogram-based BCIs in facilitating both communicative interactions and motor function recovery. Additionally, it highlights the current research gap in intuitive "stop" mechanisms within motor rehabilitation protocols, emphasizing the need for advancements that prioritize patient safety and individualized responsiveness. Furthermore, it advocates for more focused research that considers the unique requirements of ICU environments to address the challenges arising from patient variability, fatigue, and limited applicability of current BCI systems outside of experimental settings.

A comprehensive guide to BCI-based stroke neurorehabilitation interventions

Brain-Computer Interfaces (BCIs) offer the potential to facilitate neurorehabilitation in stroke patients by decoding user intentions from the central nervous system, thereby enabling control over external devices. Despite their promise, the diverse range of intervention parameters and technical challenges in clinical settings have hindered the accumulation of substantial evidence supporting the efficacy and effectiveness of BCIs in stroke rehabilitation. This article introduces a practical guide designed to navigate through these challenges in conducting BCI interventions for stroke rehabilitation. Applicable regardless of infrastructure and study design limitations, this guide acts as a comprehensive reference for executing BCI-based stroke interventions. Furthermore, it encapsulates insights gleaned from administering hundreds of BCI rehabilitation sessions to stroke patients.•Presents a comprehensive methodology for implementing BCI-based upper extremity therapy in stroke patients.•Provides detailed guidance on the number of sessions, trials, as well as the necessary hardware and software for effective intervention.

Continuous versus discrete robotic feedback for brain-computer interfaces aimed for neurorehabilitation

Introduction

Brain-Computer Interfaces (BCI) can allow control of external devices using motor imagery (MI) decoded from electroencephalography (EEG). Although BCI have a wide range of applications including neurorehabilitation, the low spatial resolution of EEG, coupled to the variability of cortical activations during MI, make control of BCI based on EEG a challenging task.

Methods

An assessment of BCI control with different feedback timing strategies was performed. Two different feedback timing strategies were compared, comprised by passive hand movement provided by a robotic hand orthosis. One of the timing strategies, the continuous, involved the partial movement of the robot immediately after the recognition of each time segment in which hand MI was performed. The other feedback, the discrete, was comprised by the entire movement of the robot after the processing of the complete MI period. Eighteen healthy participants performed two sessions of BCI training and testing, one with each feedback.

Results

Significantly higher BCI performance (65.4 ± 17.9% with the continuous and 62.1 ± 18.6% with the discrete feedback) and pronounced bilateral alpha and ipsilateral beta cortical activations were observed with the continuous feedback.

Discussion

It was hypothesized that these effects, although heterogenous across participants, were caused by the enhancement of attentional and closed-loop somatosensory processes. This is important, since a continuous feedback timing could increase the number of BCI users that can control a MI-based system or enhance cortical activations associated with neuroplasticity, important for neurorehabilitation applications.

The effect of visual and proprioceptive feedback on sensorimotor rhythms during BCI training

Brain–computer interfaces (BCI) can be designed with several feedback modalities. To promote appropriate brain plasticity in therapeutic applications, the feedback should guide the user to elicit the desired brain activity and preferably be similar to the imagined action. In this study, we employed magnetoencephalography (MEG) to measure neurophysiological changes in healthy subjects performing motor imagery (MI) -based BCI training with two different feedback modalities. The MI-BCI task used in this study lasted 40–60 min and involved imagery of right- or left-hand movements. 8 subjects performed the task with visual and 14 subjects with proprioceptive feedback. We analysed power changes across the session at multiple frequencies in the range of 4–40 Hz with a generalized linear model to find those frequencies at which the power increased significantly during training. In addition, the power increase was analysed for each gradiometer, separately for alpha (8–13 Hz), beta (14–30 Hz) and gamma (30–40 Hz) bands, to find channels showing significant linear power increase over the session. These analyses were applied during three different conditions: rest, preparation, and MI. Visual feedback enhanced the amplitude of mainly high beta and gamma bands (24–40 Hz) in all conditions in occipital and left temporal channels. During proprioceptive feedback, in contrast, power increased mainly in alpha and beta bands. The alpha-band enhancement was found in multiple parietal, occipital, and temporal channels in all conditions, whereas the beta-band increase occurred during rest and preparation mainly in the parieto-occipital region and during MI in the parietal channels above hand motor regions. Our results show that BCI training with proprioceptive feedback increases the power of sensorimotor rhythms in the motor cortex, whereas visual feedback causes mainly a gamma-band increase in the visual cortex. MI-BCIs should involve proprioceptive feedback to facilitate plasticity in the motor cortex.

Brain-Computer Interface Coupled to a Robotic Hand Orthosis for Stroke Patients' Neurorehabilitation: A Crossover Feasibility Study

Brain-Computer Interfaces (BCI) coupled to robotic assistive devices have shown promise for the rehabilitation of stroke patients. However, little has been reported that compares the clinical and physiological effects of a BCI intervention for upper limb stroke rehabilitation with those of conventional therapy. This study assesses the feasibility of an intervention with a BCI based on electroencephalography (EEG) coupled to a robotic hand orthosis for upper limb stroke rehabilitation and compares its outcomes to conventional therapy. Seven subacute and three chronic stroke patients (M = 59.9 ± 12.8) with severe upper limb impairment were recruited in a crossover feasibility study to receive 1 month of BCI therapy and 1 month of conventional therapy in random order. The outcome measures were comprised of: Fugl-Meyer Assessment of the Upper Extremity (FMA-UE), Action Research Arm Test (ARAT), motor evoked potentials elicited by transcranial magnetic stimulation (TMS), hand dynamometry, and EEG. Additionally, BCI performance and user experience were measured. All measurements were acquired before and after each intervention. FMA-UE and ARAT after BCI (23.1 ± 16; 8.4 ± 10) and after conventional therapy (21.9 ± 15; 8.7 ± 11) were significantly higher (p < 0.017) compared to baseline (17.5 ± 15; 4.3 ± 6) but were similar between therapies (p > 0.017). Via TMS, corticospinal tract integrity could be assessed in the affected hemisphere of three patients at baseline, in five after BCI, and four after conventional therapy. While no significant difference (p > 0.05) was found in patients’ affected hand strength, it was higher after the BCI therapy. EEG cortical activations were significantly higher over motor and non-motor regions after both therapies (p < 0.017). System performance increased across BCI sessions, from 54 (50, 70%) to 72% (56, 83%). Patients reported moderate mental workloads and excellent usability with the BCI. Outcome measurements implied that a BCI intervention using a robotic hand orthosis as feedback has the potential to elicit neuroplasticity-related mechanisms, similar to those observed during conventional therapy, even in a group of severely impaired stroke patients. Therefore, the proposed BCI system could be a suitable therapy option and will be further assessed in clinical trials.

Subject-Specific feature selection for near infrared spectroscopy based brain-computer interfaces

BACKGROUND AND OBJECTIVE

Brain-computer interfaces (BCIs) enable people to control an external device by analyzing the brain's neural activity. Functional near-infrared spectroscopy (fNIRS), which is an emerging optical imaging technique, is frequently used in non-invasive BCIs. Determining the subject-specific features is an important concern in enhancing the classification accuracy as well as reducing the complexity of fNIRS based BCI systems. In this study, the effectiveness of subject-specific feature selection on classification accuracy of fNIRS signals is examined.

METHODS

In order to determine the subject-specific optimal feature subsets, stepwise regression analysis based on sequential feature selection (SWR-SFS) and ReliefF methods were employed. Feature selection is applied on time-domain features of fNIRS signals such as mean, slope, peak, skewness and kurtosis values of signals. Linear discriminant analysis, k nearest neighborhood and support vector machines are employed to evaluate the performance of the selected feature subsets. The proposed techniques are validated on benchmark motor imagery (MI) and mental arithmetic (MA) based fNIRS datasets collected from 29 healthy subjects.

RESULTS

Both SWR-SFS and reliefF feature selection methods have significantly improved the classification accuracy. However, the best results (88.67% (HbR) and 86.43% (HbO) for MA dataset and 77.01% (HbR) and 71.32% (HbO) for MI dataset) were achieved using SWR-SFS while feature selection provided extremely high feature reduction rates (89.50% (HbR) and 93.99% (HbO) for MA dataset and 94.04% (HbR) and 97.73% (HbO) for MI dataset).

CONCLUSIONS

The results of the study indicate that employing feature selection improves both MA and MI-based fNIRS signals classification performance significantly.

Enhanced Motor Imagery Based Brain- Computer Interface via FES and VR for Lower Limbs

Motor imagery based brain-computer interface (MI-BCI) has been studied for improvement of patients' motor function in neurorehabilitation and motor assistance. However, the difficulties in performing imagery tasks limit its application. To overcome the limitation, an enhanced MI-BCI based on functional electrical stimulation (FES) and virtual reality (VR) is proposed in this study. On one hand, the FES is used to stimulate the subjects' lower limbs before their imagination to make them experience the muscles' contraction and improve their attention on the lower limbs, by which it is supposed that the subjects' motor imagery (MI) abilities can be enhanced. On the other hand, a ball-kicking movement scenario from the first-person perspective is designed to provide visual guidance for performing MI tasks. The combination of FES and VR can be used to reduce the difficulties in performing MI tasks and improve classification accuracy. Finally, the comparison experiments were conducted on twelve healthy subjects to validate the performance of the enhanced MI-BCI. The results show that the classification performance can be improved significantly by using the proposed MI-BCI in terms of the classification accuracy (ACC), the area under the curve (AUC) and the F1 score (paired t-test, ).

Brain-computer interface performance analysis of monozygotic twins with discordant hand dominance: A case study

Brain-computer interfaces (BCI) decode user's intentions to control external devices. However, performance variations across individuals have limited their use to laboratory environments. Handedness could contribute to these variations, especially when motor imagery (MI) tasks are used for BCI control. To further understand how handedness affects BCI control, performance differences between two monozygotic twins were analysed during offline movement and MI tasks, and while twins controlled a BCI using right-hand MI. Quantitative electroencephalography (qEEG), brain structures' volumes, and neuropsychological tests were assessed to evaluate physiological, anatomical and psychological relationships with BCI performance. Results showed that both twins had good motor imagery and attention abilities, similar volumes on most subcortical brain structures, more pronounced event-related desynchronization elicited by the twin performing non-dominant MI, and that this twin also obtained significant higher performances with the BCI. Linear regression analysis implied a strong association between twins' BCI performance, and more pronounced cortical activations in the contralateral hemisphere relative to hand MI. Therefore, it is possible that BCI performance was related with the ability of each twin to elicit cortical activations during hand MI, and less associated with subcortical brain structures' volumes and neuropsychological tests.