Scholarlink

Background <p>Functional and aesthetic deficits in individuals with facial nerve paralysis (FNP) significantly impair their quality of life. By decoding motor intentions and controlling rehabilitation devices, motor imagery (MI)-based brain-computer interfaces can improve outcomes in people with peripheral paralysis. However, the electroencephalography (EEG) features underlying different facial MIs and their decodability remain unclear. This study aims to investigate the feasibility of decoding facial MIs related to major mimetic muscles and to explore suitable decoding strategies.</p> Methods <p>Following a preliminary comparison between block and event-related designs, 20 healthy participants performed four types of facial MIs (eyebrow raising, eye closing, lip puckering and grinning) in two modalities: kinesthetic and visual, from which event-related desynchronization/synchronization (ERD/S) features were extracted using time–frequency analysis. A deep learning model was then developed for both within-subject and cross-subject decoding and benchmarked against three mainstream EEG decoding models (EEGNet, DeepConvNet, and ShallowConvNet). Finally, the proposed decoding strategy was further evaluated on EEG data from six individuals with FNP.</p> Results <p>Facial MIs induced prominent low-frequency ERD in the left prefrontal and right central-temporal regions, co-occurring with shorter and weaker ERS in higher frequencies. Regarding MI decoding, the model outperformed the baselines and achieved the highest average accuracy of 85.17% in within-subject classification of kinesthetic MI, with EEG features from the left frontal and parietal regions contributing more to decoding. Using this strategy, evaluation on patients yielded an average accuracy of 83.81% with halved training data, remaining at 76.46% after further channel reduction.</p> Conclusion <p>This study demonstrated that major mimetic muscle-related MIs can be accurately recognized from EEG using deep learning, with within-subject classification of kinesthetic MI representing the most effective decoding strategy among the evaluated conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding motor imagery related to major mimetic muscles from electroencephalography

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月25日

查看全文
  • Haoran Sun,
  • Mengkun Ding,
  • Xiaofeng Shan,
  • Shang Xie,
  • Dongming Chang,
  • Nianming Zuo,
  • Zhigang Cai

摘要

Background

Functional and aesthetic deficits in individuals with facial nerve paralysis (FNP) significantly impair their quality of life. By decoding motor intentions and controlling rehabilitation devices, motor imagery (MI)-based brain-computer interfaces can improve outcomes in people with peripheral paralysis. However, the electroencephalography (EEG) features underlying different facial MIs and their decodability remain unclear. This study aims to investigate the feasibility of decoding facial MIs related to major mimetic muscles and to explore suitable decoding strategies.

Methods

Following a preliminary comparison between block and event-related designs, 20 healthy participants performed four types of facial MIs (eyebrow raising, eye closing, lip puckering and grinning) in two modalities: kinesthetic and visual, from which event-related desynchronization/synchronization (ERD/S) features were extracted using time–frequency analysis. A deep learning model was then developed for both within-subject and cross-subject decoding and benchmarked against three mainstream EEG decoding models (EEGNet, DeepConvNet, and ShallowConvNet). Finally, the proposed decoding strategy was further evaluated on EEG data from six individuals with FNP.

Results

Facial MIs induced prominent low-frequency ERD in the left prefrontal and right central-temporal regions, co-occurring with shorter and weaker ERS in higher frequencies. Regarding MI decoding, the model outperformed the baselines and achieved the highest average accuracy of 85.17% in within-subject classification of kinesthetic MI, with EEG features from the left frontal and parietal regions contributing more to decoding. Using this strategy, evaluation on patients yielded an average accuracy of 83.81% with halved training data, remaining at 76.46% after further channel reduction.

Conclusion

This study demonstrated that major mimetic muscle-related MIs can be accurately recognized from EEG using deep learning, with within-subject classification of kinesthetic MI representing the most effective decoding strategy among the evaluated conditions.