Beyond passive observation: feedback anticipation and observation activate the mirror system in virtual finger movement control via P300-BCI DOI Creative Commons
Nikolay Syrov, Lev Yakovlev, Andrei Miroshnikov

et al.

Frontiers in Human Neuroscience, Journal Year: 2023, Volume and Issue: 17

Published: May 4, 2023

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

Language: Английский

A Review of Brain Activity and EEG-Based Brain–Computer Interfaces for Rehabilitation Application DOI Creative Commons
Mostafa Orban, Mahmoud Elsamanty, Kai Guo

et al.

Bioengineering, Journal Year: 2022, Volume and Issue: 9(12), P. 768 - 768

Published: Dec. 5, 2022

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

Language: Английский

Citations

54

International Journal of e-Collaboration (IJeC) DOI Creative Commons

Huina Gao,

Ravindra Luhach,

Muhammed Alshehri

et al.

International Journal of e-Collaboration, Journal Year: 2023, Volume and Issue: 19(2), P. 1 - 24

Published: Jan. 23, 2023

In researching cognitive or motor learning aspects of activity control, imagery (MI) is a widely used model. Research has shown that training can aid in memorizing functions because the functional associations it shares with physical movement. Because high level contact these sports, players are more likely to sustain finger injuries. As group machine techniques, web services designed solve AI-related challenges. they modular, be easily integrated into any program, making AI accessible everyone. Some performers return play early defensive splinting, taping, and casting depending on damage position played. Other injuries, predominantly necessitating full use their hand for position, require extended rehabilitation period lengthy time away from field. Therefore, this paper proposes imagery-based system (MIFRS) sports injury rehabilitation.

Language: Английский

Citations

26

Challenges and Opportunities for the Future of Brain-Computer Interface in Neurorehabilitation DOI Creative Commons
Colin Simon, David A. E. Bolton, Niamh Kennedy

et al.

Frontiers in Neuroscience, Journal Year: 2021, Volume and Issue: 15

Published: July 2, 2021

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

Language: Английский

Citations

43

Poststroke motor, cognitive and speech rehabilitation with brain–computer interface: a perspective review DOI Creative Commons
Ravikiran Mane, Zhenhua Wu, David Wang

et al.

Stroke and Vascular Neurology, Journal Year: 2022, Volume and Issue: 7(6), P. 541 - 549

Published: July 19, 2022

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

Language: Английский

Citations

31

Classification Algorithm for Electroencephalogram-based Motor Imagery Using Hybrid Neural Network with Spatio-temporal Convolution and Multi-head Attention Mechanism DOI
Xingbin Shi, Baojiang Li, Wenlong Wang

et al.

Neuroscience, Journal Year: 2023, Volume and Issue: 527, P. 64 - 73

Published: July 29, 2023

Language: Английский

Citations

23

Advanced Electrode Technologies for Noninvasive Brain–Computer Interfaces DOI
Sen Lin, Jingjing Jiang, Kai Huang

et al.

ACS Nano, Journal Year: 2023, Volume and Issue: 17(24), P. 24487 - 24513

Published: Dec. 8, 2023

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

Language: Английский

Citations

17

Determining optimal mobile neurofeedback methods for motor neurorehabilitation in children and adults with non-progressive neurological disorders: a scoping review DOI Creative Commons
Ahad Behboodi,

Walker A. Lee,

Victoria S. Hinchberger

et al.

Journal of NeuroEngineering and Rehabilitation, Journal Year: 2022, Volume and Issue: 19(1)

Published: Sept. 28, 2022

Abstract Background Brain–computer interfaces (BCI), initially designed to bypass the peripheral motor system externally control movement using brain signals, are additionally being utilized for rehabilitation in stroke and other neurological disorders. Also called neurofeedback training, multiple approaches have been developed link motor-related cortical signals assistive robotic or electrical stimulation devices during active training with variable, but mostly positive, functional outcomes reported. Our specific research question this scoping review was: persons non-progressive injuries who potential improve voluntary control, which mobile BCI-based methods demonstrate associated improved Neurorehabilitation applications? Methods We searched PubMed, Web of Science, Scopus databases all steps from study selection data extraction performed independently by at least 2 individuals. Search terms included: machine computer interfaces, motor; however, only studies requiring a attempt, versus imagery, were retained. Data included participant characteristics, design details outcomes. Results From 5109 papers, 139 full texts reviewed 23 unique identified. All EEG and, except one, on population. The most commonly reported Fugl-Meyer Assessment (FMA; n = 13) Action Research Arm Test (ARAT; 6) then assess effectiveness, evaluate features, correlate doses. Statistically functionally significant pre-to post changes seen FMA, not ARAT. did differ between feedback paradigms. Notably, FMA positively correlated dose. Conclusion This confirms previous findings effectiveness improving some evidence enhanced neuroplasticity adults stroke. Associative learning paradigms emerged more recently may be particularly feasible effective Neurorehabilitation. More clinical trials pediatric adult neurorehabilitation refine doses compare evidence-based strategies warranted.

Language: Английский

Citations

20

BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery DOI
Xingfu Wang, Yu Wang,

Wenxia Qi

et al.

Neural Networks, Journal Year: 2023, Volume and Issue: 170, P. 312 - 324

Published: Nov. 18, 2023

Language: Английский

Citations

12

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 DOI Creative Commons
Ahad Behboodi, Julia E. Kline,

Andrew Gravunder

et al.

Frontiers in Human Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: April 3, 2024

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

Language: Английский

Citations

5

Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness DOI Creative Commons
Aleksandar Miladinović, Agostino Accardo,

Joanna Jarmolowska

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(18), P. 6125 - 6125

Published: Sept. 22, 2024

Brain–computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically false positive rate, optimize temporal parameters MI-BCI systems. We investigated impact window on employing Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP), Support Vector Machine (SVM) data acquired from six post-stroke patients external BCI IVa dataset. EEG signals were recorded processed using Common Spatial Patterns (CSP) algorithm feature extraction. Our results indicate that longer generally enhance reduce positives across all classifiers, with LDA performing best. However, maintain responsiveness, practical applications, must be struck. The suggest an optimal 1–2 s, offering trade-off performance excessive delay guarantee responsiveness. These findings underscore importance optimization in systems improve usability real rehabilitation scenarios.

Language: Английский

Citations

5