arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1812.04079eess.SPcs.LGstat.ML
收藏

DOSED:一种深度学习方法,用于检测EEG信号中的多个睡眠微事件

DOSED: a deep learning approach to detect multiple sleep micro-events in EEG signal

Stanford University(斯坦福大学);Dreem(Dreem公司);Télécom ParisTech(巴黎高等电信学院);Université Paris-Saclay(巴黎萨克雷大学);Inria(法国国家信息与自动化研究所);CEA Neurospin(法国原子能委员会神经自旋研究所)

Stanislas Chambon, Valentin Thorey, Pierrick J. Arnal, Emmanuel Mignot, Alexandre Gramfort

摘要:

背景:脑电图(EEG)监测睡眠期间的大脑活动,并用于识别睡眠障碍。在睡眠医学中,临床医生在所谓的睡眠阶段解释原始EEG信号,这些睡眠阶段由专家分配给每30秒的信号窗口。对于诊断,他们还依赖于较短的原型微架构事件,这些事件表现出可变的持续时间和形状,例如纺锤体,K复合体或觉醒。注释这些事件传统上是由受过训练的睡眠专家执行的,使得该过程耗时、繁琐并且受到评分者间差异的影响。为了自动化这个过程,已经开发了各种方法,但是这些方法是特定于事件的,并且依赖于手工制作的特征的提取。新方法:我们提出了一种新的深度学习架构,称为Dreem One Shot Event Detector(DOSED)。DOSED联合预测EEG时间序列中事件的位置、持续时间和类型。本文所提出的方法应用于与睡眠相关的微架构事件,其灵感来自于为计算机视觉开发的对象检测器,如YOLO和SSD。它依赖于一个卷积神经网络,该网络从原始EEG信号中构建特征表示,以及分别执行定位和分类的两个模块。结果和与其他方法的比较:所提出的方法在4个数据集和3种类型的事件(纺锤波,K复合波,唤醒)上进行了测试,并与当前最先进的检测算法进行了比较。结论:结果表明,这种新方法的多功能性和改进的性能相比,目前国家的最先进的检测方法。

英文摘要:

Background: Electroencephalography (EEG) monitors brain activity during sleep and is used to identify sleep disorders. In sleep medicine, clinicians interpret raw EEG signals in so-called sleep stages, which are assigned by experts to every 30s window of signal. For diagnosis, they also rely on shorter prototypical micro-architecture events which exhibit variable durations and shapes, such as spindles, K-complexes or arousals. Annotating such events is traditionally performed by a trained sleep expert, making the process time consuming, tedious and subject to inter-scorer variability. To automate this procedure, various methods have been developed, yet these are event-specific and rely on the extraction of hand-crafted features. New method: We propose a novel deep learning architecure called Dreem One Shot Event Detector (DOSED). DOSED jointly predicts locations, durations and types of events in EEG time series. The proposed approach, applied here on sleep related micro-architecture events, is inspired by object detectors developed for computer vision such as YOLO and SSD. It relies on a convolutional neural network that builds a feature representation from raw EEG signals, as well as two modules performing localization and classification respectively. Results and comparison with other methods: The proposed approach is tested on 4 datasets and 3 types of events (spindles, K-complexes, arousals) and compared to the current state-of-the-art detection algorithms. Conclusions: Results demonstrate the versatility of this new approach and improved performance compared to the current state-of-the-art detection methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑