混合脑机接口-功能性电刺激运动康复系统的构建与验证

doi:10.3969/j.issn.1673-5765.2025.09.002

摘要/Abstract

摘要： 目的通过融合运动想象（motor imagery，MI）与周围视野稳态视觉诱发电位（steady-state visual evoked potential，SSVEP），构建混合脑机接口（brain-computer interface，BCI）-功能性电刺激（functional electrical stimulation，FES）运动康复系统，为卒中患者手部运动功能恢复提供新型神经康复手段。
方法选取符合纳入标准的健康受试者，构建混合BCI-FES运动康复系统。实验过程中，在中央视野呈现手部抓握视频以引导受试者进行手部MI，同时在周围视野呈现高频视觉闪烁以诱发SSVEP。采用滤波器组公共空间模式和扩展型任务相关成分分析算法分别检测MI和SSVEP信号，并通过基于分类概率和相关系数的融合策略确定视觉任务的最终分类结果，进而触发FES实现手部运动。
结果研究共纳入11名健康受试者，包括5名女性和6名男性，平均年龄为（24.3±1.6）岁。健康受试者的在线实验结果显示，BCI-FES运动康复系统的平均分类准确率达到98.48%，显著高于传统单一范式的准确率。
结论本研究构建了一种融合MI与SSVEP的BCI-FES运动康复系统，并验证了其可行性，为运动障碍患者的康复训练提供了创新方案。

文章导读： 融合MI和周围视野SSVEP的混合BCI-FES运动康复系统实现了高准确度FES控制，为运动障碍康复治疗提供了创新性的解决方案。

关键词: 脑机接口; 运动想象; 稳态视觉诱发电位; 功能性电刺激; 神经康复

Abstract: Objective To provide a novel neurorehabilitation approach for hand motor function recovery in stroke patients, a hybrid brain-computer interface (BCI)-functional electrical stimulation (FES) motor rehabilitation system was developed by integrating motor imagery (MI) and peripheral steady-state visual evoked potential (SSVEP).
Methods Healthy subjects who met the inclusion criteria were selected to construct a hybrid BCI-FES motor rehabilitation system. During the experiment, hand-grasping videos were displayed in the central visual field to guide subjects in performing hand MI, while high-frequency visual flickers were presented in the peripheral visual field to elicit SSVEP. The filter bank common spatial pattern and extended task-related component analysis algorithms were employed to detect MI and SSVEP signals, respectively. A fusion strategy based on classification probability and correlation coefficient was used to determine the final classification result, which subsequently triggered FES to induce hand movement.
Results A total of 11 healthy subjects were enrolled in the study, including 5 females and 6 males, with a mean age of (24.3±1.6) years. Online experimental results from healthy subjects demonstrated that the average classification accuracy of the BCI-FES motor rehabilitation system reached 98.48%, significantly outperforming traditional single-paradigm approaches.
Conclusions This study developed a BCI-FES motor rehabilitation system integrating MI and SSVEP, validated its feasibility, and provided an innovative solution for rehabilitation training in patients with motor dysfunction.

Key words: Brain-computer interface; Motor imagery; Steady-state visual evoked potential; Functional electrical stimulation; Neurorehabilitation

中图分类号:

R74
R318

王瑶, 李雨涵, 陈小刚. 混合脑机接口-功能性电刺激运动康复系统的构建与验证[J]. 中国卒中杂志, 2025, 20(9): 1079-1086.

WANG Yao, LI Yuhan, CHEN Xiaogang. Construction and Validation of the Hybrid Brain-Computer Interface-Functional Electrical Stimulation Motor Rehabilitation System[J]. Chinese Journal of Stroke, 2025, 20(9): 1079-1086.

参考文献

[1] KRAKAUER J W，CARMICHAEL S T. Broken movement：the neurobiology of motor recovery after stroke[M]. Cambridge：MIT Press，2017：25-40.
[2] 张冰冰. 早期康复护理对颅脑外伤术后运动障碍患者功能恢复的影响[J]. 中国医药指南，2020，18（34）：162-163.
ZHANG B B. Effect of early rehabilitation nursing on functional recovery of patients with dysfunction after craniocerebral trauma operation[J]. Guide of China Medicine，2020，18（34）：162-163.
[3] CORTES M，THICKBROOM G W，VALLS-SOLE J，et al. Spinal associative stimulation：a non-invasive stimulation paradigm to modulate spinal excitability[J]. Clin Neurophysiol，2011，122（11）：2254-2259.
[4] NOVAK I，MORGAN C，FAHEY M，et al. State of the evidence traffic lights 2019：systematic review of interventions for preventing and treating children with cerebral palsy[J/OL]. Curr Neurol Neurosci Rep，2020，20：3[2025-06-20]. https://doi.org/10.1007/s11910-020-1022-z.
[5] 李晓光，苏国辉. 治愈中枢神经系统疾病的核心科学问题——新生神经元[J]. 中国科学：生命科学，2022，52（10）：1423-1425.
LI X G，SO K F. The core scientific issues in curing central nervous system diseases—newborn neurons[J]. Sci Sin Vitae，2022，52（10）：1423-1425.
[6] ORBAN M，ELSAMANTY M，GUO K，et al. A review of brain activity and EEG-based brain-computer interfaces for rehabilitation application[J/OL]. Bioengineering，2022，9：768[2025-06-20]. https://doi.org/10.3390/bioengineering9120768.
[7] NOJIMA I，SUGATA H，TAKEUCHI H，et al. Brain-computer interface training based on brain activity can induce motor recovery in patients with stroke：a meta-analysis[J]. Neurorehabil Neural Repair，2022，36（2）：83-96.
[8] LAZAROU I，NIKOLOPOULOS S，PETRANTONAKIS P C，et al. EEG-based brain-computer interfaces for communication and rehabilitation of people with motor impairment：a novel approach of the 21st century[J/OL]. Front Hum Neurosci，2018，12：14[2025-06-20]. https://doi.org/10.3389/fnhum.2018.00014.
[9] CHAUDHARY U，BIRBAUMER N，RAMOS-MURGUIALDAY A. Brain-computer interfaces for communication and rehabilitation[J]. Nat Rev Neurol，2016，12（9）：513-525.
[10] BOCKBRADER M A，FRANCISCO G，LEE R，et al. Brain computer interfaces in rehabilitation medicine[J/OL]. PM&R，2018，10（9 Suppl 2）：S233-S243[2025-06-20]. https://doi.org/10.1016/j.pmrj.2018.05.028.
[11] 王瑶，李雨涵，崔红岩，等. 基于脑机接口的功能性电刺激研究综述[J]. 生物医学工程学杂志，2024，41（4）：650-655.
WANG Y，LI Y H，CUI H Y，et al. A review of functional electrical stimulation based on brain-computer interface[J]. Journal of Biomedical Engineering，2024，41（4）：650-655.
[12] 姜山杉，邱芷晴，尤婷婷，等. 脑卒中后功能障碍基于运动想象脑机接口应用处方研究[J]. 康复学报，2025，35（2）：212-220.
JIANG S S，QIU Z Q，YOU T T，et al. Application prescription of brain-computer interface based on motor imagery in post-stroke dysfunction[J]. Rehabilitation Medicine，2025，35（2）：212-220.
[13] WANG L，LIU X C，LIANG Z W，et al. Analysis and classification of hybrid BCI based on motor imagery and speech imagery[J/OL]. Measurement，2019，147：106842[2025-06-20]. https://doi.org/10.1016/j.measurement.2019.07.070.
[14] DENG H D，LI M F，ZUO H X，et al. Personalized motor imagery prediction model based on individual difference of ERP[J/OL]. J Neural Eng，2024，21（1）：016027[2025-06-20]. https://doi.org/10.1088/1741-2552/ad29d6.
[15] 李新，吴迎年，李睿. 基于稳态视觉诱发电位的脑电信号分类算法比较[J]. 科学技术与工程，2021，21（19）：8106-8112.
LI X，WU Y N，LI R. Comparison of electro‑encephalogram signal classification algorithms based on steady state visual evoked potential[J]. Science Technology and Engineering，2021，21（19）：8106-8112.
[16] SUN Y K，LI Y H，CHEN Y Z，et al. Efficient dual-frequency SSVEP brain-computer interface system exploiting interocular visual resource disparities[J/OL]. Expert Syst Appl，2024，252（Part A）：124144[2025-06-20]. https://doi.org/10.1016/j.eswa.2024.124144.
[17] ANG K K，CHIN Z Y，ZHANG H H，et al. Filter bank common spatial pattern（FBCSP）in brain-computer interface[C]//IEEE World Congress on Computational Intelligence. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks. Hong Kong：IEEE，2008：2390-2397.
[18] NAKANISHI M，WANG Y J，CHEN X G，et al. Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis[J]. IEEE Trans Biomed Eng，2018，65（1）：104-112.
[19] 陈小刚. 高速率稳态视觉诱发电位脑-机接口的关键技术研究[D]. 北京：清华大学，2015.
CHEN X G. Studies of key techniques for high-speed steady-state visual evoked potential-based brain-computer interface[D]. Beijing：Tsinghua University，2015.
[20] 刘彦俊. 面向运动想象脑电信号的时空频特征识别研究[D]. 广州：广州大学，2022.
LIU Y J. Research on spatio-temporal-frequency feature recognition of motor imagery EEG signals[D]. Guangzhou：Guangzhou University，2022.
[21] ABDULLAH，FAYE I，ISLAM M R. EEG channel selection techniques in motor imagery applications：a review and new perspectives[J/OL]. Bioengineering，2022，9：726[2025-06-20]. https://doi.org/10.3390/bioengineering9120726.
[22] GENG X Z，LI D Z，CHEN H L，et al. An improved feature extraction algorithms of EEG signals based on motor imagery brain-computer interface[J]. Alexandria Engineering Journal，2022，61（6）：4807-4820.
[23] XIE X F，YU Z L，LU H P，et al. Motor imagery classification based on bilinear sub-manifold learning of symmetric positive-definite matrices[J]. IEEE Trans Neural Syst Rehabil Eng，2016，25（6）：504-516.
[24] ZHANG R，XU Z X，ZHANG L P，et al. The effect of stimulus number on the recognition accuracy and information transfer rate of SSVEP-BCI in augmented reality[J/OL]. J Neural Eng，2022，19（3）：036010[2025-06-20]. https://doi.org/10.1088/1741-2552/ac6ae5.
[25] SADEGHI S，MALEKI A. Accurate estimation of information transfer rate based on symbol occurrence probability in brain-computer interfaces[J/OL]. Biomedical Signal Processing and Control，2019，54：101607[2025-06-20]. https://doi.org/10.1016/j.bspc.2019.101607.
[26] CHEN X G，WANG Y J，NAKANISHI M，et al. High-speed spelling with a noninvasive brain-computer interface[J/OL]. Proc Natl Acad Sci USA，2015，112（44）：E6058-E6067[2025-06-20]. https://doi.org/10.1073/pnas.1508080112.
[27] DENG Y，SUN Q Y，WANG C，et al. TRCA-Net：using TRCA filters to boost the SSVEP classification with convolutional neural network[J/OL]. J Neural Eng，2023，20（4）：046005[2025-06-20]. https://doi.org/10.1088/1741-2552/ace380.
[28] SADEGHI S，MALEKI A. Recent advances in hybrid brain-computer interface systems：a technological and quantitative review[J]. Basic Clin Neurosci，2018，9（5）：373-388.
[29] CHEN X G，WANG Y J，GAO S K，et al. Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface[J/OL]. J Neural Eng，2015，12（4）：046008[2025-06-20]. https://doi.org/10.1088/1741-2560/12/4/046008.
[30] XIE J X，PENG M Q，LU J Q，et al. Enhancement of event-related desynchronization in motor imagery based on transcranial electrical stimulation[J/OL]. Front Hum Neurosci，2021，15：635351[2025-06-20]. https://doi.org/10.3389/fnhum.2021.635351.
[31] ZHANG L，CHEN L，WANG Z P，et al. Enhancing motor imagery performance by antiphasic 10 Hz transcranial alternating current stimulation[J/OL]. IEEE Trans Neural Syst Rehabil Eng，2023，31：2747-2757[2025-06-20].
https://doi.org/10.1109/TNSRE.2023.3286419.
[32] HAIRE C M，VUONG V，TREMBLAY L，et al. Effects of therapeutic instrumental music performance and motor imagery on chronic post-stroke cognition and affect：a randomized controlled trial[J]. NeuroRehabilitation，2021，48（2）：195-208.
[33] 韩洪莉，张莎莎. 运动想象疗法联合重复经颅磁刺激对脊髓损伤患者躯干控制能力及肢体运动功能恢复的影响[J]. 中华养生保健，2024，42（16）：65-68.
HAN H L，ZHANG S S. The influence of motor imagery therapy combined with repetitive transcranial magnetic stimulation on trunk control ability and limb motor function recovery in patients with spinal cord injury[J]. Chinese Health Care，2024，42（16）：65-68.
[34] BIASIUCCI A，LEEB R，ITURRATE I，et al. Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke[J/OL]. Nat Commun，2018，9（1）：2421[2025-06-20]. https://doi.org/10.1038/s41467-018-04673-z.
[35] OSUAGWU B C，WALLACE L，FRASER M，et al. Rehabilitation of hand in subacute tetraplegic patients based on brain computer interface and functional electrical stimulation：a randomised pilot study[J/OL]. J Neural Eng，2016，13（6）：065002[2025-06-20]. https://doi.org/10.1088/1741-2560/13/6/065002.