Department of Psychiatry, School of Medicine, New York University, New York, NY 10016, United States of America.
J Neural Eng. 2019 Jun;16(3):036004. doi: 10.1088/1741-2552/ab0933. Epub 2019 Feb 21.
Sleep spindles have been implicated in memory consolidation and synaptic plasticity during NREM sleep. Detection accuracy and latency in automatic spindle detection are critical for real-time applications.
Here we propose a novel deep learning strategy (SpindleNet) to detect sleep spindles based on a single EEG channel. While the majority of spindle detection methods are used for off-line applications, our method is well suited for online applications.
Compared with other spindle detection methods, SpindleNet achieves superior detection accuracy and speed, as demonstrated in two publicly available expert-validated EEG sleep spindle datasets. Our real-time detection of spindle onset achieves detection latencies of 150-350 ms (~two-three spindle cycles) and retains excellent performance under low EEG sampling frequencies and low signal-to-noise ratios. SpindleNet has good generalization across different sleep datasets from various subject groups of different ages and species.
SpindleNet is ultra-fast and scalable to multichannel EEG recordings, with an accuracy level comparable to human experts, making it appealing for long-term sleep monitoring and closed-loop neuroscience experiments.
睡眠梭形波被认为与非快速眼动（NREM）睡眠期间的记忆巩固和突触可塑性有关。自动梭形波检测的准确性和潜伏期对于实时应用至关重要。
在这里，我们提出了一种新的基于单个脑电图（EEG）通道的深度学习策略（SpindleNet）来检测睡眠梭形波。虽然大多数的梭形波检测方法都用于离线应用，但我们的方法非常适合在线应用。
与其他梭形波检测方法相比，SpindleNet 在两个公开的经过专家验证的 EEG 睡眠梭形波数据集上实现了更高的检测准确性和速度。我们对梭形波起始的实时检测达到了 150-350ms 的检测潜伏期（~两个到三个梭形波周期），并且在低 EEG 采样频率和低信噪比下仍保持出色的性能。SpindleNet 在来自不同年龄和物种的不同受试者群体的不同睡眠数据集上具有良好的泛化能力。
SpindleNet 非常快速且可扩展到多通道 EEG 记录，其准确性可与人类专家相媲美，因此非常适合长期睡眠监测和闭环神经科学实验。
