用于睡眠精准分期的多模态生理时频特征提取网络  

Multi-modal physiological time-frequency feature extraction network for accurate sleep stage classification

作　　者：胡凯蕾 陈景霞[1] 张鹏伟[1] 雪雯 谢佳[1] HU Kailei;CHEN Jingxia;ZHANG Pengwei;XUE Wen;XIE Jia(School of Electronic Information and Artificial Intelligence,Shaanxi University of Science and Technology,Xi’an 710021,P.R.China)

机构地区：[1]陕西科技大学电子信息与人工智能学院,西安710021

出　　处：《生物医学工程学杂志》2024年第1期26-33,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金(61806118);陕西科技大学科研启动基金(2020BJ-30)。

摘　　要：睡眠分期对临床疾病诊断以及睡眠质量评估至关重要。现有睡眠分期方法大多通过单通道或单模态信号,使用单分支深层卷积网络进行特征提取,这不仅阻碍了睡眠相关多样性特征的捕获,增加了计算代价,而且对睡眠分期的准确率也有一定的影响。为解决这一问题,本文提出一种端到端的用于睡眠精准分期的多模态生理时频特征提取网络(MTFF-Net)。首先,利用短时傅里叶变换(STFT)将包含脑电(EEG)、心电(ECG)、眼电(EOG)、肌电(EMG)的多模态生理信号转换为二维时频特征图;然后,使用多尺度EEG紧凑卷积网络(Ms-EEGNet)与双向门控循环(Bi-GRU)网络相结合的时频特征提取网络,捕获与睡眠特征波形相关的多尺度频谱特征以及与睡眠阶段转换相关的时序特征。根据美国睡眠医学学会(AASM)EEG睡眠分期判据,该模型在科英布拉大学系统与机器人研究所第三组子睡眠数据集(ISRUC-S3)上的五分类任务中取得了84.3%的准确率,其宏观F1分数(m-F1)的值为83.1%,科恩卡帕(Cohen's Kappa)系数为79.8%。实验结果表明,本文所提模型实现了更高的分类准确率,推进了深度学习算法在辅助临床决策中的应用。Sleep stage classification is essential for clinical disease diagnosis and sleep quality assessment.Most of the existing methods for sleep stage classification are based on single-channel or single-modal signal,and extract features using a single-branch,deep convolutional network,which not only hinders the capture of the diversity features related to sleep and increase the computational cost,but also has a certain impact on the accuracy of sleep stage classification.To solve this problem,this paper proposes an end-to-end multi-modal physiological time-frequency feature extraction network(MTFF-Net)for accurate sleep stage classification.First,multi-modal physiological signal containing electroencephalogram(EEG),electrocardiogram(ECG),electrooculogram(EOG)and electromyogram(EMG)are converted into two-dimensional time-frequency images containing time-frequency features by using short time Fourier transform(STFT).Then,the time-frequency feature extraction network combining multi-scale EEG compact convolution network(Ms-EEGNet)and bidirectional gated recurrent units(Bi-GRU)network is used to obtain multi-scale spectral features related to sleep feature waveforms and time series features related to sleep stage transition.According to the American Academy of Sleep Medicine(AASM)EEG sleep stage classification criterion,the model achieved 84.3%accuracy in the five-classification task on the third subgroup of the Institute of Systems and Robotics of the University of Coimbra Sleep Dataset(ISRUC-S3),with 83.1%macro F1 score value and 79.8%Cohen’s Kappa coefficient.The experimental results show that the proposed model achieves higher classification accuracy and promotes the application of deep learning algorithms in assisting clinical decision-making.

关 键 词：睡眠分期 生理信号 多模态 多尺度 双向门控循环网络 

分 类 号：R740[医药卫生—神经病学与精神病学] TN911.7[医药卫生—临床医学] TP183[电子电信—通信与信息系统]