A Sequential End-to-End Neonatal Sleep Staging Model with Squeeze and Excitation Blocks and Sequential Multi-Scale Convolution Neural Networks
International Journal of Neural Systems · 2024
DOI: 10.1142/s0129065724500138 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Neural Systems, 2024. Verfasst von Hangyu Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Center for Intelligent Medical Electronics, School of Information Science and Technology, Fudan University, Shanghai 200433, P. R. China. Hauptthemen laut MEDLINE: Electroencephalography, Sleep. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: the National Key Research and Development Program of China, the National Natural Science Foundation of China.
Abstract (Originalsprache)
Automatic sleep staging offers a quick and objective assessment for quantitatively interpreting sleep stages in neonates. However, most of the existing studies either do not encompass any temporal information, or simply apply neural networks to exploit temporal information at the expense of high computational overhead and modeling ambiguity. This limits the application of these methods to multiple scenarios. In this paper, a sequential end-to-end sleep staging model, SeqEESleepNet, which is competent for parallelly processing sequential epochs and has a fast training rate to adapt to different scenarios, is proposed. SeqEESleepNet consists of a sequence epoch generation (SEG) module, a sequential multi-scale convolution neural network (SMSCNN) and squeeze and excitation (SE) blocks. The SEG module expands independent epochs into sequential signals, enabling the model to learn the temporal information between sleep stages. SMSCNN is a multi-scale convolution neural network that can extract both multi-scale features and temporal information from the signal. Subsequently, the followed SE block can reassign the weights of features through mapping and pooling. Experimental results exhibit that in a clinical dataset, the proposed method outperforms the state-of-the-art approaches, achieving an overall accuracy, F1-score, and Kappa coefficient of 71.8%, 71.8%, and 0.684 on a three-class classification task with a single channel EEG signal. Based on our overall results, we believe the proposed method could pave the way for convenient multi-scenario neonatal sleep staging methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Intelligent Medical Electronics, School of Information Science and Technology, Fudan University, Shanghai 200433, P. R. China.
- Department of Neurology, Children's Hospital of Fudan University, National Children's Medical Center, Shanghai, P. R. China.
- Human Phenome Institute, Fudan University, 825 Zhangheng Road, Shanghai 201203, P. R. China.
ORCID-Profile: Hangyu Zhu, Yan Xu, Yonglin Wu, Ning Shen, Laishuan Wang, Chen Chen, Wei Chen
Förderung
- the National Key Research and Development Program of China
- the National Natural Science Foundation of China
Zitieren
APA
Zhu, H., Xu, Y., Wu, Y., Shen, N., Wang, L., Chen, C., & Chen, W. (2024). A Sequential End-to-End Neonatal Sleep Staging Model with Squeeze and Excitation Blocks and Sequential Multi-Scale Convolution Neural Networks. International Journal of Neural Systems. https://doi.org/10.1142/s0129065724500138
Vancouver
Zhu H, Xu Y, Wu Y, Shen N, Wang L, Chen C, et al. A Sequential End-to-End Neonatal Sleep Staging Model with Squeeze and Excitation Blocks and Sequential Multi-Scale Convolution Neural Networks. International Journal of Neural Systems. 2024. doi:10.1142/s0129065724500138
BibTeX
@article{Zhu2024,
author = {Zhu, Hangyu and Xu, Yan and Wu, Yonglin and Shen, Ning and Wang, Laishuan and Chen, Chen and Chen, Wei},
title = {A Sequential End-to-End Neonatal Sleep Staging Model with Squeeze and Excitation Blocks and Sequential Multi-Scale Convolution Neural Networks},
journal = {International Journal of Neural Systems},
year = {2024},
doi = {10.1142/s0129065724500138}
}
EUVIMED