A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification
Sleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep da...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10217021/ |
| _version_ | 1797736988374204416 |
|---|---|
| author | Haotian Yao Tao Liu Ruiyang Zou Shengnan Ding Yan Xu |
| author_facet | Haotian Yao Tao Liu Ruiyang Zou Shengnan Ding Yan Xu |
| author_sort | Haotian Yao |
| collection | DOAJ |
| description | Sleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep data makes models hard to train from scratch. Here, we propose a vision Transformer-based architecture to process multi-channel polysomnogram signals. The method is an end-to-end framework that consists of a spatial encoder, a temporal encoder, and an MLP head classifier. The spatial encoder using a pre-trained Vision Transformer captures spatial information from multiple PSG channels. The temporal encoder utilizing the self-attention mechanism understands transitions between nearby epochs. In addition, we introduce a tailored image generation method to extract features within multi-channel and reshape them for transfer learning. We validate our method on 3 datasets and outperform the state-of-the-art algorithms. Our method fully explores the spatial-temporal relationship among different brain regions and addresses the problem of data insufficiency in clinical environments. Benefiting from reformulating the problem as image classification, the method could be applied to other 1D-signal problems in the future. |
| first_indexed | 2024-03-12T13:21:52Z |
| format | Article |
| id | doaj.art-f2323b7a48744963b0b0cece8d47184e |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-12T13:21:52Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-f2323b7a48744963b0b0cece8d47184e2023-08-25T23:00:05ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01313353336210.1109/TNSRE.2023.330520110217021A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage ClassificationHaotian Yao0https://orcid.org/0009-0002-3025-3773Tao Liu1https://orcid.org/0000-0001-7098-4285Ruiyang Zou2Shengnan Ding3https://orcid.org/0009-0007-3144-6266Yan Xu4https://orcid.org/0000-0002-2636-7594Department of Information Technology and Electrical Engineering, ETH Zürich, Zürich, SwitzerlandDepartment of Bioengineering, Imperial College London, London, U.K.Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, ChinaBeijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, ChinaBeijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, ChinaSleep stage classification is a fundamental task in diagnosing and monitoring sleep diseases. There are 2 challenges that remain open: (1) Since most methods only rely on input from a single channel, the spatial-temporal relationship of sleep signals has not been fully explored. (2) Lack of sleep data makes models hard to train from scratch. Here, we propose a vision Transformer-based architecture to process multi-channel polysomnogram signals. The method is an end-to-end framework that consists of a spatial encoder, a temporal encoder, and an MLP head classifier. The spatial encoder using a pre-trained Vision Transformer captures spatial information from multiple PSG channels. The temporal encoder utilizing the self-attention mechanism understands transitions between nearby epochs. In addition, we introduce a tailored image generation method to extract features within multi-channel and reshape them for transfer learning. We validate our method on 3 datasets and outperform the state-of-the-art algorithms. Our method fully explores the spatial-temporal relationship among different brain regions and addresses the problem of data insufficiency in clinical environments. Benefiting from reformulating the problem as image classification, the method could be applied to other 1D-signal problems in the future.https://ieeexplore.ieee.org/document/10217021/EEGsleep stage classificationtransformertransfer learningdata transformation |
| spellingShingle | Haotian Yao Tao Liu Ruiyang Zou Shengnan Ding Yan Xu A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification IEEE Transactions on Neural Systems and Rehabilitation Engineering EEG sleep stage classification transformer transfer learning data transformation |
| title | A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification |
| title_full | A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification |
| title_fullStr | A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification |
| title_full_unstemmed | A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification |
| title_short | A Spatial-Temporal Transformer Architecture Using Multi-Channel Signals for Sleep Stage Classification |
| title_sort | spatial temporal transformer architecture using multi channel signals for sleep stage classification |
| topic | EEG sleep stage classification transformer transfer learning data transformation |
| url | https://ieeexplore.ieee.org/document/10217021/ |
| work_keys_str_mv | AT haotianyao aspatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT taoliu aspatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT ruiyangzou aspatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT shengnanding aspatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT yanxu aspatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT haotianyao spatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT taoliu spatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT ruiyangzou spatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT shengnanding spatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification AT yanxu spatialtemporaltransformerarchitectureusingmultichannelsignalsforsleepstageclassification |