Chang Liang, Yang Banghua, Zhang Jiayang, Li Tie, Feng Juntao, Xu Wendong
School of Mechatronic Engineering and Automation, Research Center of Brain-Computer Engineering, Shanghai University, Shanghai, 200444 China.
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, 300072 China.
Cogn Neurodyn. 2025 Dec;19(1):118. doi: 10.1007/s11571-025-10296-0. Epub 2025 Jul 23.
Accurate decoding and strong feature interpretability of Motor Imagery (MI) are expected to drive MI applications in stroke rehabilitation. However, the inherent nonstationarity and high intra-class variability of MI-EEG pose significant challenges in extracting reliable spatio-temporal features. We proposed the Dynamic Spatio-Temporal Feature Augmentation Network (DSTA-Net), which combines DSTA and the Spatio-Temporal Convolution (STC) modules. In DSTA module, multi-scale temporal convolutional kernels tailored to the α and β frequency bands of MI neurophysiological characteristics, while raw EEG serve as a baseline feature layer to retain original information. Next, Grouped Spatial Convolutions extract multi-level spatial features, combined with weight constraints to prevent overfitting. Spatial convolution kernels map EEG channel information into a new spatial domain, enabling further feature extraction through dimensional transformation. And STC module further extracts features and conducts classification. We evaluated DSTA-Net on three public datasets and applied it to a self-collected stroke dataset. In tenfold cross-validation, DSTA-Net achieved average accuracy improvements of 6.29% ( < 0.01), 3.05% ( < 0.01), 5.26% ( < 0.01), and 2.25% over the ShallowConvNet on the BCI-IV-2a, OpenBMI, CASIA, and stroke dataset, respectively. In hold-out validation, DSTA-Net achieved average accuracy improvements of 3.99% ( < 0.01) and 4.2% ( < 0.01) over the ShallowConvNet on the OpenBMI and CASIA datasets, respectively. Finally, we applied DeepLIFT, Common Spatial Pattern, and t-SNE to analyze the contributions of individual EEG channels, extract spatial patterns, and visualize features. The superiority of DSTA-Net offers new insights for further research and application in MI. The code is available in https://github.com/CL-Cloud-BCI/DSTANet-code.
运动想象（MI）的准确解码和强大的特征可解释性有望推动其在中风康复中的应用。然而，MI-EEG固有的非平稳性和高类内变异性在提取可靠的时空特征方面带来了重大挑战。我们提出了动态时空特征增强网络（DSTA-Net），它结合了DSTA和时空卷积（STC）模块。在DSTA模块中，针对MI神经生理特征的α和β频段定制了多尺度时间卷积核，而原始脑电图作为基线特征层以保留原始信息。接下来，分组空间卷积提取多级空间特征，并结合权重约束以防止过拟合。空间卷积核将脑电图通道信息映射到一个新的空间域，通过维度变换实现进一步的特征提取。并且STC模块进一步提取特征并进行分类。我们在三个公共数据集上评估了DSTA-Net，并将其应用于自行收集的中风数据集。在十折交叉验证中，DSTA-Net在BCI-IV-2a、OpenBMI、CASIA和中风数据集上分别比浅卷积网络（ShallowConvNet）平均准确率提高了6.29%（<0.01）、3.05%（<0.01）、5.26%（<0.01）和2.25%。在留出验证中，DSTA-Net在OpenBMI和CASIA数据集上分别比浅卷积网络平均准确率提高了3.99%（<0.01）和4.2%（<0.01）。最后，我们应用DeepLIFT、共同空间模式和t-SNE来分析各个脑电图通道的贡献、提取空间模式并可视化特征。DSTA-Net的优越性为MI的进一步研究和应用提供了新的见解。代码可在https://github.com/CL-Cloud-BCI/DSTANet-code获取。
