EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis
By: Chen Wang , Yansen Wang , Dongqi Han and more
Potential Business Impact:
Finds important brain signals for computers.
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.
Similar Papers
AI-Driven SEEG Channel Ranking for Epileptogenic Zone Localization
Signal Processing
Finds important brain signals for seizures faster.
Activity Coefficient-based Channel Selection for Electroencephalogram: A Task-Independent Approach
Neurons and Cognition
Finds brain signals faster for mind control.
A Brain Wave Encodes a Thousand Tokens: Modeling Inter-Cortical Neural Interactions for Effective EEG-based Emotion Recognition
Neurons and Cognition
Reads your feelings from brain waves.