Retrieving Filter Spectra in CNN for Explainable Sleep Stage Classification

TL;DR

This paper introduces an explainability tool for CNN-based sleep stage classification that reveals how spectral processing influences model decisions, aiding interpretability and potential performance improvements.

Contribution

The study presents a novel spectral retrieval tool for CNN filters, enhancing understanding of spectral processing in sleep stage models and guiding model optimization.

Findings

Spectral processing mainly influences lower frequency bands.

Models prioritize the most informative EEG channels.

Insights can be used to improve model performance.

Abstract

Despite significant advances in deep learning-based sleep stage classification, the clinical adoption of automatic classification models remains slow. One key challenge is the lack of explainability, as many models function as black boxes with millions of parameters. In response, recent work has increasingly focussed on enhancing model explainability. This study contributes to these efforts by introducing an explainability tool for spectral processing of individual EEG channels. Specifically, this tools retrieves the filter spectrum of low-level convolutional feature extraction and compares it with the classification-relevant spectral information in the data. We apply our tool on the EEGNet and MSA-CNN models using the ISRUC-S3 and Sleep-EDF-20 datasets. The tool reveals that spectral processing plays a significant role in the lower frequency bands. In addition, comparing the correlation between filter spectrum and data-derived spectral information with univariate performance indicates that the model naturally prioritises the most informative channels in a multimodal setting. We specify how these insights can be leveraged to enhance model performance. The code for the filter spectrum retrieval and its analysis is available at https://github.com/sgoerttler/MSA-CNN.