Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring

By Albert Vilamala, Kristoffer Hougaard Madsen, Lars Kai Hansen. 2017

150 citations recorded by the source corpus.

Sleep studies are important for diagnosing sleep disorders such as insomnia, narcolepsy or sleep apnea. They rely on manual scoring of sleep stages from raw polisomnography signals, which is a tedious visual task requiring the workload of highly trained professionals. Consequently, research efforts to purse for an automatic stage scoring based on machine learning techniques have been carried out over the last years. In this work, we resort to multitaper spectral analysis to create visually interpretable images of sleep patterns from EEG signals as inputs to a deep convolutional network trained to solve visual recognition tasks. As a working example of transfer learning, a system able to accurately classify sleep stages in new unseen patients is presented. Evaluations in a widely-used publicly available dataset favourably compare to state-of-the-art results, while providing a framework for visual interpretation of outcomes.

Subfields: Cognitive Neuroscience, Physiology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Physiology

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “brain, neuro* breast [68], lung [6], [81], [47], [67], [130], [152] sleep [153], skin [154] [131], [132], [135], [155] others [105] Method.”
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging (2019, unknown): “ results across 7 datasets. U-Time and our CNN-LSTM baseline process singlechannel EEG data. Referenced models process single- or multi-channel EEG data. References: [1] [Supratak et al., 2017], [2] [Vilamala et al., 2017], [3] [Phan et al., 2018], [4] [Tsinalis et al., 2016], [5] [Andreotti et al.,”
Deep learning-based electroencephalography analysis: a systematic review (2019, methodology): “In [209], the class imbalance problem was addressed by randomly balancing all classes while sampling for each training epoch.”
Deep learning for electroencephalogram (EEG) classification tasks: a review (2019, unknown): “[40] CNN ReLU (conv) C2I—Spect N/A N/A SS 86.”
XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (2020, unknown): “0 − − − − − − − − − − − − − − VGG-FT [51] 80.”
Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection (2020, background): “Language Processing [9], as well as various niche areas such as protein binding prediction [10], [11], machine vibration analysis [12] and medical signal processing [13].”
A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series (2017, background): “Methods in the second category consist in learning appropriate feature representations from transformed data [5], [8]–[10] or directly from raw data with convolutional neural networks [11]–[13].”
SleepTransformer: Automatic Sleep Staging With Interpretability and Uncertainty Quantification (2021, background): “We argue that two overarching obstacles need to be addressed for a machine scoring system to work alongside practitioners in an interactive and collaborative manner: (1) interpretability [34], [35] and (2) uncertainty quantiﬁcation [36].”