Visualising convolutional neural network decisions in automated sleep scoring

Current sleep medicine relies on the supervised analysis of polysomnographic recordings, which comprise amongst others electroencephalogram (EEG), electromyogram (EMG), and electrooculogram (EOG) signals. Convolutional neural networks (CNN) provide an interesting framework for automated sleep classification, however, the lack of interpretability of its results has hampered CNN's further use in medicine. In this study, we train a CNN using as input Continuous Wavelet transformed EEG, EOG and EMG recordings from a publicly available dataset. The network achieved a 10-fold cross-validation Cohen's Kappa score of $\kappa = 0.71 \pm 0.01$. Further, we provide insights on how this network classifies individual epochs of sleep using Guided Gradient-weighted Class Activation Maps (Guided Grad-CAM). The proposed approach is able to produce fine-grained activation maps on time-frequency domain for each signal providing a useful tool for identifying relevant features in CNNs.

[1]  Stanislas Chambon,et al.  A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[3]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[4]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[5]  Andrea Vedaldi,et al.  Understanding deep image representations by inverting them , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[7]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[8]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[9]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[13]  Aeilko H. Zwinderman,et al.  Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG , 2000, IEEE Transactions on Biomedical Engineering.

[14]  Lars Kai Hansen,et al.  Visualization of nonlinear kernel models in neuroimaging by sensitivity maps , 2011, NeuroImage.

[15]  P. Anderer,et al.  Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard , 2009, Journal of sleep research.

[16]  Maarten De Vos,et al.  DNN Filter Bank Improves 1-Max Pooling CNN for Single-Channel EEG Automatic Sleep Stage Classification , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Andrea Vedaldi,et al.  Interpretable Explanations of Black Boxes by Meaningful Perturbation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Chao Wu,et al.  DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[20]  C. O’Reilly,et al.  Montreal Archive of Sleep Studies: an open‐access resource for instrument benchmarking and exploratory research , 2014, Journal of sleep research.

[21]  Lars Kai Hansen,et al.  Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

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

[23]  R. Foster,et al.  Sleep and circadian rhythm disruption in psychiatric and neurodegenerative disease , 2010, Nature Reviews Neuroscience.

[24]  Athanasios Tsanas,et al.  Stage-independent, single lead EEG sleep spindle detection using the continuous wavelet transform and local weighted smoothing , 2015, Front. Hum. Neurosci..

[25]  Maarten De Vos,et al.  Multichannel Sleep Stage Classification and Transfer Learning using Convolutional Neural Networks , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[26]  E. Wolpert.  A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[27]  Yike Guo,et al.  Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks , 2016, ArXiv.