Score: 2

EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis

Published: October 15, 2025 | arXiv ID: 2510.13592v1

By: Chen Wang , Yansen Wang , Dongqi Han and more

BigTech Affiliations: Microsoft

Potential Business Impact:

Finds important brain signals for computers.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
πŸ‡¨πŸ‡³ πŸ‡ΊπŸ‡Έ United States, China

Page Count
17 pages

Category
Computer Science:
Machine Learning (CS)