A1 Journal article (refereed)
Interpretable Sleep Stage Classification Based on Layer-Wise Relevance Propagation (2024)
Zhou, D., Xu, Q., Zhang, J., Wu, L., Xu, H., Kettunen, L., Chang, Z., Zhang, Q., & Cong, F. (2024). Interpretable Sleep Stage Classification Based on Layer-Wise Relevance Propagation. IEEE Transactions on Instrumentation and Measurement, 73, Article 3511710. https://doi.org/10.1109/tim.2024.3370799
JYU authors or editors
Publication details
All authors or editors: Zhou, Dongdong; Xu, Qi; Zhang, Jiacheng; Wu, Lei; Xu, Hongming; Kettunen, Lauri; Chang, Zheng; Zhang, Qiang; Cong, Fengyu
Journal or series: IEEE Transactions on Instrumentation and Measurement
ISSN: 0018-9456
eISSN: 1557-9662
Publication year: 2024
Publication date: 27/02/2024
Volume: 73
Article number: 3511710
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Publication country: United States
Publication language: English
DOI: https://doi.org/10.1109/tim.2024.3370799
Publication open access: Not open
Publication channel open access:
Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/100095
Abstract
Numerous deep learning-based methodologies have been proposed to facilitate automatic sleep stage classification tasks. Nevertheless, the black-box nature of these approaches is one of the skeptical factors hindering clinical application. Toward model interpretability, this study presents a novel interpretable sleep stage classification scheme based on layer-wise relevance propagation (LRP). We first adopt the short-time Fourier transform (STFT) to convert the raw electroencephalogram (EEG) signals to the time-frequency images, which could visually demonstrate EEG patterns of each sleep stage. Moreover, we introduce an efficient convolutional neural network (CNN)-based model, namely MSSENet, that assembles with the multiscale CNN (MSCNN) module and residual squeeze-and-excitation (R-SE) block for the image input. The LRP method is eventually applied to evaluate the contribution of each frequency pixel in the input time-frequency image to the model prediction. Experimental findings show that the MSSENet could outperform or achieve comparable performance to other state-of-the-art approaches on three polysomnography (PSG) datasets. Furthermore, through utilizing the heat mapping, the LRP-based explainability results validate the high relevance of specific EEG patterns to the prediction of the corresponding sleep stage, which is consistent with the sleep scoring guidelines.
Keywords: sleep; classification; EEG; signal analysis; signal processing
Free keywords: sleep; brain modeling; electroencephalography; time-frequency analysis; data models; recording; feature extraction
Contributing organizations
Ministry reporting: Yes
VIRTA submission year: 2024
Preliminary JUFO rating: 3