Wang Jiaheng, Yao Lin, Wang Yueming
IEEE Trans Neural Syst Rehabil Eng. 2025;33:2834-2846. doi: 10.1109/TNSRE.2025.3591254.
A growing amount of deep learning models for motor imagery (MI) decoding from electroencephalogram (EEG) have demonstrated their superiority over traditional machine learning approaches in offline dataset analysis. However, current online MI-based brain-computer interfaces (BCIs) still predominantly adopt machine learning decoders while falling short of high BCI performance. Yet, the generalization and advantages of deep learning-based EEG decoding in realistic BCI systems remain far unclear.
We conduct a randomized and cross-session online MI-BCI study on 2D center-out tasks in 15 BCI-naive subjects. A newly proposed deep learning model named interactive frequency convolutional neural network (IFNet) is leveraged and rigorously compared with the prevailing benchmark namely filter-bank common spatial pattern (FBCSP) for online MI decoding.
Through extensive online analysis, the deep learning decoder consistently outperforms the classical counterpart across various performance metrics. In particular, IFNet significantly improves the average online task accuracy by 20% and 27% in two sessions compared with FBCSP, respectively. Moreover, a significant cross-session training effect is observed by the IFNet model ( ${P}={0}.{017}$ ) while not for the controlled method ( ${P}={0}.{337}$ ). Further offline evaluations also demonstrate the superior performance of IFNet over state-of-the-art deep learning models. Moreover, we present unique behavioral and neurophysiological insights underlying online brain-machine interaction.
We present one of the first studies about online MI-BCIs using deep learning, achieving substantially enhanced online performance for continuous BCI control.
This study suggests the good utility of deep learning in MI-BCIs and has implications for clinical applications such as stroke rehabilitation.
越来越多用于从脑电图（EEG）中解码运动想象（MI）的深度学习模型在离线数据集分析中已证明其优于传统机器学习方法。然而，当前基于在线MI的脑机接口（BCI）仍主要采用机器学习解码器，同时缺乏高BCI性能。然而，基于深度学习的EEG解码在实际BCI系统中的泛化能力和优势仍远未明确。
我们对15名未接触过BCI的受试者进行了关于二维中心向外任务的随机交叉会话在线MI-BCI研究。利用一种新提出的名为交互式频率卷积神经网络（IFNet）的深度学习模型，并将其与用于在线MI解码的主流基准即滤波器组公共空间模式（FBCSP）进行了严格比较。
通过广泛的在线分析，深度学习解码器在各种性能指标上始终优于传统对应方法。特别是，与FBCSP相比，IFNet在两个会话中分别将平均在线任务准确率显著提高了20%和27%。此外，IFNet模型观察到显著的跨会话训练效果（P = 0.017），而对照方法则未观察到（P = 0.337）。进一步的离线评估也证明了IFNet优于现有最先进的深度学习模型。此外，我们还展示了在线脑机交互背后独特的行为和神经生理学见解。
我们展示了首批关于使用深度学习的在线MI-BCI的研究之一，实现了连续BCI控制的在线性能大幅提升。
本研究表明深度学习在MI-BCI中的良好效用，并对中风康复等临床应用具有启示意义。
