SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach
SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach
复制标题
DOI：
10.1371/journal.pone.0216456
复制
发表时间：
2019-05-07
期刊：
影响因子：
3.7
通讯作者：
Acharya, U. Rajendra
中科院分区：
文献类型：
--
作者：
Mousavi, Sajad;Afghah, Fatemeh;Acharya, U. Rajendra
脑电(EEG)是监测大脑活动和诊断睡眠障碍的常用基础信号。人工睡眠阶段评分对于睡眠专家来说是一项耗时的任务，而且受到评分者之间可靠性的限制。本文提出了一种基于单通道脑电信号的睡眠阶段自动标注方法SleepEEGNet。SleepEEGNet由深度卷积神经网络(CNN)组成，用于提取时不变特征、频率信息，以及序列到序列模型，以捕捉睡眠时段和分数之间复杂且长期的短期上下文依赖。此外，为了减少现有睡眠数据集中出现的类别失衡问题的影响，我们应用了新的损失函数，在训练网络的同时对每个睡眠阶段具有相等的误分类误差。我们从2013年和2018年发布的Physionet Sept-EDF数据集评估了该方法在不同的单一EEG通道(即Fpz-Cz和Pz-Oz EEG通道)上的性能。评估结果表明，与现有文献相比，该方法获得了最好的标注性能，总体准确率为84.26%，宏观F1评分为79.66%，kappa=0.79。我们开发的模型可以应用于其他睡眠脑电信号，帮助睡眠专家做出准确的诊断。源代码可在https://github.com/SajadMo/SleepEEGNet.上找到
Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and kappa = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.