Analyzing stereoelectroencephalography (SEEG) signals is critical for brain-computer interface (BCI) applications and neuroscience research, yet poses significant challenges due to the large number of input channels and their heterogeneous relevance. Traditional channel selection methods struggle to scale or provide meaningful interpretability for SEEG data. In this work, we propose EEGChaT, a novel Transformer-based channel selection module designed to automatically identify the most task-relevant channels in SEEG recordings. EEGChaT introduces Channel Aggregation Tokens (CATs) to aggregate information across channels, and leverages an improved Attention Rollout technique to compute interpretable, quantitative channel importance scores. We evaluate EEGChaT on the DuIN dataset, demonstrating that integrating EEGChaT with existing classification models consistently improves decoding accuracy, achieving up to 17\% absolute gains. Furthermore, the channel weights produced by EEGChaT show substantial overlap with manually selected channels, supporting the interpretability of the approach. Our results suggest that EEGChaT is an effective and generalizable solution for channel selection in high-dimensional SEEG analysis, offering both enhanced performance and insights into neural signal relevance.
翻译:立体脑电图(SEEG)信号分析对于脑机接口(BCI)应用和神经科学研究至关重要,但由于输入通道数量庞大且其相关性异质,带来了重大挑战。传统的通道选择方法难以扩展或为SEEG数据提供有意义的可解释性。在本工作中,我们提出了EEGChaT,一种新颖的基于Transformer的通道选择模块,旨在自动识别SEEG记录中与任务最相关的通道。EEGChaT引入了通道聚合令牌(CATs)来聚合跨通道的信息,并利用改进的注意力展开技术来计算可解释的、定量的通道重要性分数。我们在DuIN数据集上评估了EEGChaT,结果表明将EEGChaT与现有分类模型集成能持续提高解码准确率,实现了高达17%的绝对增益。此外,EEGChaT产生的通道权重与手动选择的通道显示出显著重叠,支持了该方法的可解释性。我们的结果表明,EEGChaT是高维SEEG分析中一种有效且可泛化的通道选择解决方案,既提供了增强的性能,也提供了对神经信号相关性的洞察。