skip to main content
10.1145/3678935.3678942acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicbetConference Proceedingsconference-collections
research-article
Open access

A Hybrid Neonatal Sleep Staging Method based on Convolutional Neural Networks and Graph Neural Networks

Published: 12 October 2024 Publication History

Abstract

Currently, deep learning-based methods for automatic sleep staging are thriving and gaining significant traction due to the advanced pattern recognition and feature extraction inherent as compared to machine learning-based methods. However, most of the existing approaches only consider the informative features of raw signals, while neglecting the connectivity characteristics among multi-channel electroencephalogram (EEG) data. In this study, a hybrid framework for neonatal sleep staging by combining Convolutional Neural Network (CNN) and Graph Neural Network (GNN) is proposed. It not only considers brain connections among multi-channel EEG through various perspectives (such as linear temporal correlation, information-theoretic, and phase-dynamics information, etc.) but also involves the high-order structural features that originate from graphs. The method potentially enhances the feature representation, thus significantly improving neonatal sleep staging performance. The proposed method is validated on a clinical neonatal sleep dataset, demonstrating superior performance, especially with CNN+Graph Attention Network (GAT) achieving an accuracy of 74.8% and an f1-score of 0.747. The results highlight the potential of leveraging both CNN for feature learning on connectivity matrices and GNN for attention between nodes to enhance neonatal sleep staging.

References

[1]
Amir Hossein Ansari, Ofelie De Wel, Mario Lavanga, Alexander Caicedo, Anneleen Dereymaeker, Katrien Jansen, Jan Vervisch, Maarten De Vos, Gunnar Naulaers, and Sabine Van Huffel. 2018. Quiet sleep detection in preterm infants using deep convolutional neural networks. Journal of neural engineering 15, 6 (2018), 066006.
[2]
Amir H Ansari, Ofelie De Wel, Kirubin Pillay, Anneleen Dereymaeker, Katrien Jansen, Sabine Van Huffel, Gunnar Naulaers, and Maarten De Vos. 2020. A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants. Journal of Neural Engineering 17, 1 (2020), 016028.
[3]
Emadeldeen Eldele, Zhenghua Chen, Chengyu Liu, Min Wu, Chee-Keong Kwoh, Xiaoli Li, and Cuntai Guan. 2021. An attention-based deep learning approach for sleep stage classification with single-channel EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering 29 (2021), 809–818.
[4]
Yulin Gong, Fatong Wang, Yudan Lv, Chang Liu, and Tianxing Li. 2023. Automatic Sleep Staging Using BiRNN with Data Augmentation and Label Redirection. Electronics 12, 11 (2023). https://doi.org/10.3390/electronics12112394
[5]
Joonki Hong, Hai Hong Tran, Jinhwan Jung, Hyeryung Jang, Dongheon Lee, In-Young Yoon, Jung Kyung Hong, and Jeong-Whun Kim. 2022. End-to-End Sleep Staging Using Nocturnal Sounds from Microphone Chips for Mobile Devices. Nature and Science of Sleep 14 (June 2022), 1187–1201. https://doi.org/10.2147/NSS.S361270 Publisher: Dove Press.
[6]
Ziyu Jia, Youfang Lin, Jing Wang, Xiaojun Ning, Yuanlai He, Ronghao Zhou, Yuhan Zhou, and H Lehman Li-wei. 2021. Multi-view spatial-temporal graph convolutional networks with domain generalization for sleep stage classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering 29 (2021), 1977–1986.
[7]
Ziyu Jia, Youfang Lin, Jing Wang, Ronghao Zhou, Xiaojun Ning, Yuanlai He, and Yaoshuai Zhao. 2020. GraphSleepNet: Adaptive Spatial-Temporal Graph Convolutional Networks for Sleep Stage Classification. In IJCAI, Vol. 2021. 1324–1330.
[8]
Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. CoRR abs/1609.02907 (2016). arXiv:1609.02907http://arxiv.org/abs/1609.02907
[9]
Huy Phan, Fernando Andreotti, Navin Cooray, Oliver Y Chén, and Maarten De Vos. 2018. Joint classification and prediction CNN framework for automatic sleep stage classification. IEEE Transactions on Biomedical Engineering 66, 5 (2018), 1285–1296.
[10]
Huy Phan, Fernando Andreotti, Navin Cooray, Oliver Y Chén, and Maarten De Vos. 2019. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Transactions on Neural Systems and Rehabilitation Engineering 27, 3 (2019), 400–410.
[11]
Huy Phan, Oliver Y. Chén, Philipp Koch, Zongqing Lu, Ian McLoughlin, Alfred Mertins, and Maarten De Vos. 2021. Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning. IEEE Transactions on Biomedical Engineering 68, 6 (2021), 1787–1798. https://doi.org/10.1109/TBME.2020.3020381
[12]
Akara Supratak, Hao Dong, Chao Wu, and Yike Guo. 2017. DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering 25, 11 (2017), 1998–2008.
[13]
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. arxiv:1710.10903 [stat.ML]
[14]
Mingrui Xia, Jinhui Wang, and Yong He. 2013. BrainNet Viewer: a network visualization tool for human brain connectomics. PloS one 8, 7 (2013), e68910.
[15]
Dechun Zhao, Renpin Jiang, Mingyang Feng, Jiaxin Yang, Yi Wang, Xiaorong Hou, and Xing Wang. 2022. A deep learning algorithm based on 1D CNN-LSTM for automatic sleep staging. Technology and Health Care 30, 2 (2022), 323–336.
[16]
Hangyu Zhu, Yonglin Wu, Ning Shen, Jiahao Fan, Linkai Tao, Cong Fu, Huan Yu, Feng Wan, Sio Hang Pun, Chen Chen, 2022. The masking impact of intra-artifacts in EEG on deep learning-based sleep staging systems: A comparative study. IEEE Transactions on Neural Systems and Rehabilitation Engineering 30 (2022), 1452–1463.
[17]
Hangyu Zhu, Yan Xu, Ning Shen, Yonglin Wu, Laishuang Wang, Chen Chen, and Wei Chen. 2023. MS-HNN: Multi-scale Hierarchical Neural Network with Squeeze and Excitation Block for Neonatal Sleep Staging Using a Single-Channel EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering (2023).

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICBET '24: Proceedings of the 2024 14th International Conference on Biomedical Engineering and Technology
June 2024
241 pages
ISBN:9798400717628
DOI:10.1145/3678935
This work is licensed under a Creative Commons Attribution International 4.0 License.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 October 2024

Check for updates

Author Tags

  1. CNN
  2. EEG
  3. Functional connection
  4. Graph neural network
  5. Neonatal
  6. Sleep staging

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICBET 2024

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 106
    Total Downloads
  • Downloads (Last 12 months)106
  • Downloads (Last 6 weeks)40
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media