融合专注度评估与反馈的运动想象脑机接口康复训练研究

doi:10.12267/j.issn.2096-5931.2025.03.004

摘要/Abstract

摘要：

针对目前基于运动想象(Motor Imagery,MI)脑机接口的康复训练方法试验方式单一、缺乏实时反馈以及脑电解码率较低的问题,创新性地提出一种融合MI专注度评估与反馈的康复训练方法。该方法引入MI专注度解析,采用MI引导的脑电采集范式和集成专注程度评估的任务设计,提高脑电数据有效性。同时,根据被试任务态专注度评估反馈参数,实现更高效解码。实验结果表明,该训练方法提高了被试的专注度,验证了被试不同专注程度下的脑电差异,MI脑电二分类平均准确率达到84.37%。

关键词: 脑机接口, 运动想象, 专注度评估反馈优化, 康复训练

Abstract:

Current motor imagery brain-computer interface (MI-BCI) rehabilitation training methods suffer from a lack of diversity in experimental approaches, insufficient real-time feedback optimization, and low decoding rates of electroencephalogram (EEG) signals. This paper innovatively proposes an MI-BCI rehabilitation training method to address these problems, integrating concentration assessment and feedback optimization. A paradigm of EEG signals acquisition is explored by incorporating concentration level assessment. The efficiency of decoding motor imagery EEG signals is significantly improved, benefiting from the feedback of concentration assessment of the subjects in a task state. Experimental results demonstrate that the proposed novel MI-BCI rehabilitation training method improves the concentration levels of subjects, and simultaneously validates the differences in EEG signals with varying degree of concentration. Furthermore, an MI-EEG binary classification accuracy of 84.37% is achieved.

Key words: BCI, motor imagery, integrating concentration assessment and feedback, rehabilitation training

中图分类号:

D920.1

范雪梅, 满建志, 张慧, 龙善丽, 孙光宇. 融合专注度评估与反馈的运动想象脑机接口康复训练研究[J]. 信息通信技术与政策, 2025, 51(3): 25-35.

FAN Xuemei, MAN Jianzhi, ZHANG Hui, LONG Shanli, SUN Guangyu. Research on motor imagery brain-computer interface rehabilitation training method incorporating attention assessment and feedback[J]. Information and Communications Technology and Policy, 2025, 51(3): 25-35.

导出引用管理器 EndNote|Ris|BibTeX

链接本文:

http://ictp.caict.ac.cn/CN/10.12267/j.issn.2096-5931.2025.03.004

http://ictp.caict.ac.cn/CN/Y2025/V51/I3/25

图/表 10

参考文献 25

[1]	COSCIA M, WESSEL M J, CHAUDARY U, et al. Neurotechnology-aided interventions for upper limb motor rehabilitation in severe chronic stroke[J]. Brain, 2019, 142(8):2182-2197. doi: 10.1093/brain/awz181 pmid: 31257411
[2]	CHEN L, ZHANG H. Personalized rehabilitation: bridging the gap with AI and robotics[J]. International Journal of Physical Medicine & Rehabilitation, 2023, 11(3), 301-310.
[3]	YOSHIMOTO T, SHIMIZU I, HIROI Y. Sustained effects of once-a-week gait training with hybrid-assistive limb for rehabilitation in chronic stroke: case study[J]. Journal of Physical Therapy Science, 2016, 28(9): 2684-2687.
[4]	KIM S, PARK J. Smart rehabilitation systems: addressing the limitations of traditional therapy[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32(1):45-53.
[5]	ABIRI R, BORHANI S, SELLERS E W, et al. A comprehensive review of EEG-based brain-computer interface paradigms[J]. Journal of Neural Engineering, 2019, 16(1): 011001.
[6]	杨帮华, 张永怀. 基于卷积神经网络提高脑卒中患者二分类运动想象任务识别准确率的可行性研究[J]. 上海医学, 2024, 47(4):253-258.
[7]	WANG T, DU S, DONG E. A novel method to reduce the motor imagery BCI illiteracy[J]. Medical & Biological Engineering & Computing, 2021, 59(11-12):2205-2217.
[8]	LI L, ZHANG Y, HUANG L, et al. Robot assisted treatment of hand functional rehabilitation based on visual motor imagination[J]. Frontiers in Aging Neuroscience, 2022, 14: 870871.
[9]	LI M, XU G, XIE J, et al. A review: motor rehabilitation after stroke with control based on human intent[J]. Journal of Engineering in Medicine, 2018, 232(4): 344-360.
[10]	RAMOS M A, BROETZ D, REA M, et al. Brain-machine interface in chronic stroke rehabilitation: a controlled study[J]. Annals of Neurology, 2013, 74(1): 100-108.
[11]	LI M, LIU Y, WU Y, et al. Neurophysiological substrates of stroke patients with motor imagery-based brain-computer interface training[J]. International Journal of Neuroscience, 2014, 124(6): 403-415. doi: 10.3109/00207454.2013.850082 pmid: 24079396
[12]	BIASIUCCI A, LEEB R, ITURRATE I, et al. Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke[J]. Nature Communications, 2018, 9(1): 2421. doi: 10.1038/s41467-018-04673-z pmid: 29925890
[13]	SUN Y K, CHEN X G, LIU B C, et al. Signal acquisition of brain-computer interfaces: a medical-engineering crossover perspective review[J]. Fundamental Research, 2025, 5(1):3-16.
[14]	YANG S, LI R, LI H, et al. Exploring the use of brain-computer interfaces in stroke neurorehabilitation[J]. BioMed Research International, 2021: 9967348.
[15]	ROBINSON N, MANE R, CHOUHAN T, et al. Emerging trends in BCI-robotics for motor control and rehabilitation[J]. Current Opinion in Biomedical Engineering, 2021, 20:100354.
[16]	ABIRI R, BORHANI S, SELLERS E W, et al. A comprehensive review of EEG-based brain-computer interface paradigms[J]. Journal of Neural Engineering, 2019, 16(1): 011001.
[17]	GUO N, WANG X, DUANMU D, et al. SSVEP-based brain computer interface controlled soft robotic glove for post-stroke hand function rehabilitation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 1737-1744.
[18]	SINGH P, HEERA P K, KAUR G. Expression of neuronal plasticity markers in hypoglycemia induced brain injury[J]. Molecular and Cellular Biochemistry, 2003, 247(1-2): 69-74. pmid: 12841633
[19]	QU H, ZENG F X, TANG Y B, et al. The clinical effects of brain-computer interface with robot on upper-limb function for post-stroke rehabilitation: a Meta-analysis and systematic review[J]. Disability and Rehabilitation: Assistive Technology, 2022, 19(1):30-41.
[20]	MA Z Z, WU J J, CAO Z, et al. Motor imagery-based brain-computer interface rehabilitation programs enhance upper extremity performance and cortical activation in stroke patients[J]. Journal of NeuroEngineering and Rehabilitation, 2024, 21(1): 91.
[21]	MATTLA D, PICHIORRI F, COLAMARINO E, et al. The promotoer, a brain-computer interface-assisted intervention to promote upper limb functional motor recovery after stroke: a study protocol for a randomized controlled trial to test early and long-term efficacy and to identify determinants of response[J]. BMC Neurology, 2020, 20(1):254. doi: 10.1186/s12883-020-01826-w pmid: 32593293
[22]	HAYWARD K S, SCHMIDT J, LOHSE K R, et al. Are we armed with the right data? Pooled individual data review of biomarkers in people with severe upper limb impairment after stroke[J]. NeuroImage: Clinical, 2016, 13:310-319.
[23]	王玉龙. 康复功能评定学[M]. 北京: 人民卫生出版社, 2008.
[24]	POPE A T, BOGART E H, BARTOLOME D S. Biocybernetic system evaluates indices of operator engagement in automated task[J]. Biological Psychology, 1995, 40(1-2):187-195. pmid: 7647180
[25]	ZHAO X, ZHANG H, ZHU G, et al. A multi-branch 3Dconvolutional neural network for EEG-based motor imagery classification[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2019, 27(10): 2164-2177.

模块	层	卷积核大小	参数量	输出尺寸
分支1	时域卷积	(8×1×T/10)	8×T/10+8	(8, C, T)
	深度可分离空域卷积	(8×C×1)	8×C×2+8	(8, 1, T)
	平均池化	(1×32)	/	(8, 1, T₁)
分支2	时域卷积	(8×1×T/25)	8×T/25+8	(8, 8, T)
	空域卷积	(8×C×1)	8×C×8+8	(8, 1, T)
	平均池化	(1×75)	/	(8, 1, T₂)
分支3	时空融合卷积	(8×C×T/125)	8×C×T/125+8	(8, 1, T)
分支3	平均池化	(1×75)	/	(8, 1, T₃)
融合	连接	/	/	(8, 1, T₁+T₂+T₃)
分类	卷积层	(2×1×(T₁+T₂+T₃))	2×(T₁+T₂+T₃)×8+2	(2, 1)

模块	层	卷积核大小	参数量	输出尺寸
分支1	时域卷积	(8×1×T/10)	8×T/10+8	(8, C, T)
	深度可分离空域卷积	(8×C×1)	8×C×2+8	(8, 1, T)
	平均池化	(1×32)	/	(8, 1, T₁)
分支2	时域卷积	(8×1×T/25)	8×T/25+8	(8, 8, T)
	空域卷积	(8×C×1)	8×C×8+8	(8, 1, T)
	平均池化	(1×75)	/	(8, 1, T₂)
分支3	时空融合卷积	(8×C×T/125)	8×C×T/125+8	(8, 1, T)
分支3	平均池化	(1×75)	/	(8, 1, T₃)
融合	连接	/	/	(8, 1, T₁+T₂+T₃)
分类	卷积层	(2×1×(T₁+T₂+T₃))	2×(T₁+T₂+T₃)×8+2	(2, 1)