MaskSleepNet: A Cross-Modality Adaptation Neural Network for Heterogeneous Signals Processing in Sleep Staging
- 7 March 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 27 (5) , 2353-2364
Abstract
Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.Keywords
Funding Information
- National Natural Science Foundation of China (62001118)
- National Key Research and Development Program of China (2021YFF1200600)
- Shanghai Municipal Science and Technology International Research and Development Collaboration Project (20510710500)
- Shanghai Committee of Science and Technology (20S31903900)
- National Key Research and Development Program of China (2021YFC2501404)
This publication has 43 references indexed in Scilit:
- A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral featuresJournal of Neuroscience Methods, 2016
- Computer-aided sleep staging using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and bootstrap aggregatingBiomedical Signal Processing and Control, 2016
- Dual tree complex wavelet transform for sleep state identification from single channel electroencephalogram2015
- Automatic sleep stage classification2015
- On the classification of sleep states by means of statistical and spectral features from single channel Electroencephalogram2015
- Montreal Archive of Sleep Studies: an open‐access resource for instrument benchmarking and exploratory researchJournal of Sleep Research, 2014
- Sleep: A Health ImperativeSLEEP, 2012
- The process of falling asleepSleep Medicine Reviews, 2001
- Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEGIEEE Transactions on Biomedical Engineering, 2000
- A manual of standardized terminology, techniques and scoring system for sleep stages of human subjectsElectroencephalography and Clinical Neurophysiology, 1969