Division of Pulmonary, Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai, USA.
Division of Pulmonary, Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai, USA.
J Neurosci Methods. 2021 Aug 1;360:109224. doi: 10.1016/j.jneumeth.2021.109224. Epub 2021 May 28.
Recent advancement in deep learning provides a pivotal opportunity to potentially supplement or supplant the limiting step of manual sleep scoring.
In this paper, we characterize the WaveSleepNet (WSN), a deep convolutional neural network (CNN) that uses wavelet transformed images of mouse EEG/EMG signals to autoscore sleep and wake.
WSN achieves an epoch by epoch mean accuracy of 0.86 and mean F1 score of 0.82 compared to manual scoring by a human expert. In mice experiencing mechanically induced sleep fragmentation, an overall epoch by epoch mean accuracy of 0.80 is achieved by WSN and classification of non-REM (NREM) sleep is not compromised, but the high level of sleep fragmentation results in WSN having greater difficulty differentiating REM from NREM sleep. We also find that WSN achieves similar levels of accuracy on an independent dataset of externally acquired EEG/EMG recordings with an overall epoch by epoch accuracy of 0.91. We also compared conventional summary sleep metrics in mice sleeping ad libitum. WSN systematically biases sleep fragmentation metrics of bout number and bout length leading to an overestimated degree of sleep fragmentation.
In a cross-validation, WSN has a greater macro and stage-specific accuracy compared to a conventional random forest classifier. Examining the WSN, we find that it automatically learns spectral features consistent with manual scoring criteria that are used to define each class.
These results suggest to us that WSN is capable of learning visually agreeable features and may be useful as a supplement to human manual scoring.
深度学习的最新进展为潜在地补充或取代手动睡眠评分的限制步骤提供了关键机会。
在本文中，我们描述了 WaveSleepNet（WSN），这是一种深度卷积神经网络（CNN），它使用鼠标 EEG/EMG 信号的小波变换图像来自动评分睡眠和清醒。
与人类专家的手动评分相比，WSN 在每个时期的平均准确率为 0.86，平均 F1 得分为 0.82。在经历机械诱导的睡眠碎片化的小鼠中，WSN 达到了 0.80 的整体时期平均准确率，非快速眼动（NREM）睡眠的分类不受影响，但高水平的睡眠碎片化导致 WSN 在区分 REM 和 NREM 睡眠方面更具挑战性。我们还发现，WSN 在独立获取的 EEG/EMG 记录的数据集上也达到了类似的准确率，总体时期准确率为 0.91。我们还比较了自由睡眠的小鼠的常规汇总睡眠指标。WSN 系统地偏向于 bout 数量和 bout 长度的睡眠碎片化指标，导致睡眠碎片化程度被高估。
在交叉验证中，WSN 与传统的随机森林分类器相比具有更高的宏和特定阶段的准确性。检查 WSN 时，我们发现它自动学习了与手动评分标准一致的光谱特征，这些特征用于定义每个类别。
这些结果表明，WSN 能够学习视觉上令人满意的特征，并且可能作为人工手动评分的补充有用。
