Hybrid scattering-LSTM networks for automated detection of sleep arousals
Hybrid scattering-LSTM networks for automated detection of sleep arousals
复制标题
DOI：
10.1088/1361-6579/ab2664
复制
发表时间：
2019-07-01
影响因子：
3.2
通讯作者：
Homsi, Masun Nabhan
中科院分区：
文献类型：
--
作者：
Warrick, Philip A.;Lostanlen, Vincent;Homsi, Masun Nabhan
目的：早期检测多导睡眠图（PSG）信号中的睡眠觉醒对于监测或诊断睡眠障碍以及降低进一步并发症（包括心脏病和血压波动）的风险至关重要。方法：在本文中，我们提出了一种新的自动检测器的非呼吸暂停觉醒地区的多道PSG记录。该检测器级联了四个不同的模块：具有Morlet小波的二阶散射变换（ST）;深度可分离卷积层;双向长短期记忆（BiLSTM）层;和密集层。前两项在所有渠道共享，后两项则以多渠道方式运作。遵循深度学习范式，整个架构以端到端的方式进行训练，以优化两个目标：唤醒开始和偏移的检测，以及唤醒类型的分类。主要结果及意义：该方法的新奇有三个方面：它是第一次使用混合ST-BiLSTM网络与生物医学信号;它捕获的频率信息（0.1 Hz）低于检测采样率（0.5 Hz）;它不需要明确的机制来克服数据中的类别不平衡。在2018年PhysioNet/CinC挑战赛的后续阶段，所提出的架构在隐藏测试数据上实现了0.50的精确度-召回率曲线（AUPRC）下的最先进区域，与整体第二高的官方结果并列。
Objective: Early detection of sleep arousal in polysomnographic (PSG) signals is crucial for monitoring or diagnosing sleep disorders and reducing the risk of further complications, including heart disease and blood pressure fluctuations. Approach: In this paper, we present a new automatic detector of non-apnea arousal regions in multichannel PSG recordings. This detector cascades four different modules: a second-order scattering transform (ST) with Morlet wavelets; depthwise-separable convolutional layers; bidirectional long short-term memory (BiLSTM) layers; and dense layers. While the first two are shared across all channels, the latter two operate in a multichannel formulation. Following a deep learning paradigm, the whole architecture is trained in an end-to-end fashion in order to optimize two objectives: the detection of arousal onset and offset, and the classification of the type of arousal. Main results and Significance: The novelty of the approach is three-fold: it is the first use of a hybrid ST-BiLSTM network with biomedical signals; it captures frequency information lower (0.1 Hz) than the detection sampling rate (0.5 Hz); and it requires no explicit mechanism to overcome class imbalance in the data. In the follow-up phase of the 2018 PhysioNet/CinC Challenge the proposed architecture achieved a state-of-the-art area under the precision-recall curve (AUPRC) of 0.50 on the hidden test data, tied for the second-highest official result overall.