Attentive Adversarial Network for Large-Scale Sleep Staging

Current approaches to developing a generalized automated sleep staging method rely on constructing a large labeled training and test corpora by leveraging electroencephalograms (EEGs) from different individuals. However, data in the training set may exhibit changes in the EEG pattern that are very different from the data in the test set due to inherent inter-subject variability, heterogeneity of acquisition hardware, different montage choices and different recording environments. Training an algorithm on such data without accounting for this diversity can lead to underperformance. In order to solve this issue, different methods are investigated for learning an invariant representation across all individuals in datasets. However, all parts of the corpora are not equally transferable. Therefore, forcefully aligning the nontransferable data may lead to a negative impact on the overall performance. Inspired by how clinicians manually label sleep stages, this paper proposes a method based on adversarial training along with attention mechanisms to extract transferable information across individuals from different datasets and pay attention to more important or relevant channels and transferable parts of data, simultaneously. Using two large public EEG databases 994 patient EEGs (6,561 hours of data) from the Physionet 2018 Challenge (P18C) database and 5,793 patients (42,560 hours) EEGs from Sleep Heart Health Study (SHHS) we demonstrate that adversarially learning a network with attention mechanism, significantly boosts performance compared to state-of-the-art deep learning approaches in the cross-dataset scenario. By considering the SHHS as the training set, the proposed method improves, on average, precision from 0.72 to 0.84, sensitivity from 0.74 to 0.85, and Cohen’s Kappa coefficient from 0.64 to 0.80 for the P18C database.

[1]  Bonggun Shin,et al.  Bayesian Group Nonnegative Matrix Factorization for EEG Analysis , 2012, ArXiv.

[2]  Changde Du,et al.  Domain Adaptation for EEG Emotion Recognition Based on Latent Representation Similarity , 2020, IEEE Transactions on Cognitive and Developmental Systems.

[3]  H. Colten,et al.  Sleep Disorders and Sleep Deprivation: An Unmet Public Health Problem , 2006 .

[4]  Haoqi Sun,et al.  Expert-level sleep scoring with deep neural networks , 2018, J. Am. Medical Informatics Assoc..

[5]  J. Buhmann,et al.  Automatic Human Sleep Stage Scoring Using Deep Neural Networks , 2018, Front. Neurosci..

[6]  Lenka Lhotská,et al.  An Unsupervised Multichannel Artifact Detection Method for Sleep EEG Based on Riemannian Geometry , 2019, Sensors.

[7]  Christian Igel,et al.  U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging , 2019, NeurIPS.

[8]  Kon Max Wong,et al.  Electroencephalogram signals classification for sleep-state decision - a Riemannian geometry approach , 2012, IET Signal Process..

[9]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[10]  Gari D. Clifford,et al.  Subject Selection on a Riemannian Manifold for Unsupervised Cross-subject Seizure Detection , 2017, ArXiv.

[11]  Alexander A. Fingelkurts,et al.  Nonstationary nature of the brain activity as revealed by EEG/MEG: Methodological, practical and conceptual challenges , 2005, Signal Process..

[12]  Qiao Li,et al.  You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge 2018 , 2018, 2018 Computing in Cardiology Conference (CinC).

[13]  Jimeng Sun,et al.  REST: Robust and Efficient Neural Networks for Sleep Monitoring in the Wild , 2020, WWW.

[14]  Christian Jutten,et al.  Common Spatial Pattern revisited by Riemannian geometry , 2010, 2010 IEEE International Workshop on Multimedia Signal Processing.

[15]  Michael I. Jordan,et al.  Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers , 2019, ICML.

[16]  Christian Jutten,et al.  Transfer Learning: A Riemannian Geometry Framework With Applications to Brain–Computer Interfaces , 2018, IEEE Transactions on Biomedical Engineering.

[17]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[18]  A. Chesson,et al.  The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology, and Techinical Specifications , 2007 .

[19]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[20]  David Kent,et al.  Automated Sleep Stage Scoring of the Sleep Heart Health Study Using Deep Neural Networks. , 2019, Sleep.

[21]  Necmettin Sezgin,et al.  Estimation of Sleep Stages by an Artificial Neural Network Employing EEG, EMG and EOG , 2010, Journal of Medical Systems.

[22]  Carlos D. Castillo,et al.  Generate to Adapt: Aligning Domains Using Generative Adversarial Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Spyridon Samothrakis,et al.  Bagging Adversarial Neural Networks for Domain Adaptation in Non-Stationary EEG , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[24]  Bernhard Schölkopf,et al.  Transfer Learning in Brain-Computer Interfaces , 2015, IEEE Computational Intelligence Magazine.

[25]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  He Li,et al.  Reducing the Subject Variability of EEG Signals with Adversarial Domain Generalization , 2019, ICONIP.

[27]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[28]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[29]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[30]  Jianmin Wang,et al.  Transferable Attention for Domain Adaptation , 2019, AAAI.

[31]  Dan Liu,et al.  A Fast, Efficient Domain Adaptation Technique for Cross-Domain Electroencephalography(EEG)-Based Emotion Recognition , 2017, Sensors.

[32]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[33]  Maureen Clerc,et al.  Optimal transport Applied to Transfer Learning for P300 Detection , 2017, GBCIC.

[34]  Seungjin Choi,et al.  Group Nonnegative Matrix Factorization for EEG Classification , 2009, AISTATS.

[35]  Aren Jansen,et al.  CNN architectures for large-scale audio classification , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[36]  Xianrui Zhang,et al.  Conditional Adversarial Domain Adaptation Neural Network for Motor Imagery EEG Decoding , 2020, Entropy.

[37]  P. Hanly,et al.  Minimizing Interrater Variability in Staging Sleep by Use of Computer-Derived Features. , 2016, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.

[38]  Alexandre Barachant,et al.  Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review , 2017 .

[39]  Christian Jutten,et al.  Unsupervised Cross-Subject BCI Learning and Classification using Riemannian Geometry , 2016, ESANN.

[40]  S. Quan,et al.  Rules for scoring respiratory events in sleep: update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine. , 2012, Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine.