DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model With Uncertainty Estimates
DeepSleepNet-Lite: A Simplified Automatic Sleep Stage Scoring Model With Uncertainty Estimates
复制标题
DOI：
10.1109/tnsre.2021.3117970
复制
发表时间：
2021-01-01
影响因子：
4.9
通讯作者：
Faraci, Francesca Dalia
中科院分区：
文献类型：
--
作者：
Fiorillo, Luigi;Favaro, Paolo;Faraci, Francesca Dalia
深度学习被广泛用于最新的自动睡眠评分算法。它的受欢迎程度源于其出色的性能以及处理原始信号和直接从数据中学习特征的能力。大多数现有的评分算法利用非常计算要求的架构，由于其大量的训练参数，并处理输入中的长时间序列（长达12分钟）。这些架构中只有少数提供了模型不确定性的估计。在这项研究中，我们提出了DeepSleepNet-Lite，一个简化和轻量级的评分架构，只处理90秒的EEG输入序列。我们利用，第一次在睡眠评分，蒙特卡罗辍学技术，以提高性能的架构，也检测到不确定的情况。在开源Sleep-EDF扩展数据库的单通道EEG Fpz-Cz上进行评价。与现有的最先进的架构相比，DeepSleepNet-Lite在总体准确性、宏F1评分和Cohen's kappa方面的性能略低（如果不是在标准水平上）（在Sleep-EDF v1 - 2013 +/-30分钟上：84.0%，78.0%，0.78;在Sleep-EDF v2 - 2018 +/-30分钟上：80.3%，75.2%，0.73）。蒙特卡罗丢弃使得能够估计不确定的预测。通过拒绝不确定的实例，该模型在两个版本的数据库上都实现了更高的性能（Sleep-EDF v1 - 2013 +/-30分钟：86.1.0%，79.6%，0.81; Sleep-EDF v2 - 2018 +/-30分钟：82.3%，76.7%，0.76）。我们的轻度睡眠评分方法为实时睡眠分析评分算法的应用铺平了道路。
Deep learning is widely used in the most recent automatic sleep scoring algorithms. Its popularity stems from its excellent performance and from its ability to process raw signals and to learn feature directly from the data. Most of the existing scoring algorithms exploit very computationally demanding architectures, due to their high number of training parameters, and process lengthy time sequences in input (up to 12 minutes). Only few of these architectures provide an estimate of the model uncertainty. In this study we propose DeepSleepNet-Lite, a simplified and lightweight scoring architecture, processing only 90-seconds EEG input sequences. We exploit, for the first time in sleep scoring, the Monte Carlo dropout technique to enhance the performance of the architecture and to also detect the uncertain instances. The evaluation is performed on a single-channel EEG Fpz-Cz from the open source Sleep-EDF expanded database. DeepSleepNet-Lite achieves slightly lower performance, if not on par, compared to the existing state-of-the-art architectures, in overall accuracy, macro F1-score and Cohen's kappa (on Sleep-EDF v1-2013 +/- 30mins: 84.0%, 78.0%, 0.78; on Sleep-EDF v2-2018 +/- 30mins: 80.3%, 75.2%, 0.73). Monte Carlo dropout enables the estimate of the uncertain predictions. By rejecting the uncertain instances, the model achieves higher performance on both versions of the database (on Sleep-EDF v1-2013 +/- 30mins: 86.1.0%, 79.6%, 0.81; on Sleep-EDF v2-2018 +/- 30mins: 82.3%, 76.7%, 0.76). Our lighter sleep scoring approach paves the way to the application of scoring algorithms for sleep analysis in real-time.