MRNet: a Multi-scale Residual Network for EEG-based Sleep Staging
This work provides an incremental improvement in automated sleep staging for clinicians and researchers by addressing information loss in EEG signal propagation.
This paper proposes MRNet, a multi-scale residual network combined with a Markov-based sequential correction algorithm for automated EEG-based sleep staging. The method achieves competitive performance with 85.14% accuracy and 78.91% F1 score on Sleep-EDFx, and 87.59% accuracy and 79.62% F1 score on Sleep-EDF.
Sleep staging based on electroencephalogram (EEG) plays an important role in the clinical diagnosis and treatment of sleep disorders. In order to emancipate human experts from heavy labeling work, deep neural networks have been employed to formulate automated sleep staging systems recently. However, EEG signals lose considerable detailed information in network propagation, which affects the representation of deep features. To address this problem, we propose a new framework, called MRNet, for data-driven sleep staging by integrating a multi-scale feature fusion model and a Markov-based sequential correction algorithm. The backbone of MRNet is a residual block-based network, which performs as a feature extractor.Then the fusion model constructs a feature pyramid by concatenating the outputs from the different depths of the backbone, which can help the network better comprehend the signals in different scales. The Markov-based sequential correction algorithm is designed to reduce the output jitters generated by the classifier. The algorithm depends on a prior stage distribution associated with the sleep stage transition rule and the Markov chain. Experiment results demonstrate the competitive performance of our proposed approach on both accuracy and F1 score (e.g., 85.14% Acc and 78.91% F1 score on Sleep-EDFx, and 87.59% Acc and 79.62% F1 score on Sleep-EDF).