Uncovering the structure of clinical EEG signals with self-supervised learning

  title={Uncovering the structure of clinical EEG signals with self-supervised learning},
  author={Hubert J. Banville and Omar Chehab and Aapo Hyv{\"a}rinen and Denis Alexander Engemann and Alexandre Gramfort},
  journal={Journal of Neural Engineering},
Objective. Supervised learning paradigms are often limited by the amount of labeled data that is available. This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG), where labeling can be costly in terms of specialized expertise and human processing time. Consequently, deep learning architectures designed to learn on EEG data have yielded relatively shallow models and performances at best similar to those of traditional feature-based… 

Learning with self-supervision on EEG data

Results report that linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available, and suggest that self-supervision may pave the way to a wider use of deep learning models on EEG data.

Self-supervised Contrastive Learning for EEG-based Sleep Staging

A self-supervised contrastive learning method of EEG signals for sleep stage classification by setting up a pretext task for the network to match the right transformation pairs generated from EEG signals and the robustness of the network gets improved in dealing with diverse data.

Self-supervised EEG Representation Learning for Automatic Sleep Staging

A self-supervised model, named Contrast with the World Representation (ContraWR), is proposed for EEG signal representation learning, which uses global statistics from the dataset to distinguish signals associated with different sleep stages and provides informative representations in 2D projection.

Domain-guided Self-supervision of EEG Data Improves Downstream Classification Performance and Generalizability

A domain-guided approach for learning representations of scalp-electroencephalograms (EEGs) without relying on expert annotations is presented and evidence that an encoder pretrained using the proposed SSL tasks shows strong predictive performance on multiple downstream classifications is presented.

BENDR: Using Transformers and a Contrastive Self-Supervised Learning Task to Learn From Massive Amounts of EEG Data

A single pre-trained model is capable of modeling completely novel raw EEG sequences recorded with differing hardware, and different subjects performing different tasks, outperforming prior work in more task-specific (sleep stage classification) self-supervision.

Improving self-supervised pretraining models for epileptic seizure detection from EEG data

Various self-supervision strategies to enhance the performance of a time-series based Diffusion convolution recurrent neural network (DCRNN) model are presented and the learned weights in the self- supervision pretraining phase can be transferred to the supervised training phase to boost the model’s prediction capability.

Towards Open-World EEG Decoding via Deep Learning

This article provides a comprehensive survey of DL methods for open-world EEG decoding, and identifies promising research directions to inspire future studies for EEG decoding in real-world applications.

Cross-Session Motor Imagery EEG Classification using Self-Supervised Contrastive Learning

A self-supervised contrastive learning method of cross-session based EEG data for motor imagery classification that gives the average accuracy of 50.81% and performed significantly better than the compared supervised learning-based methods.

Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability

A Self-Supervised Learning method with a pretext task of signal reconstruction to learn an informative generalized PPG representation is proposed, which suggests that SSL may pave the way for the broader use of machine learning models on PPG data in label-scarce regimes.

Toward Open-World Electroencephalogram Decoding Via Deep Learning: A comprehensive survey

This article provides a comprehensive survey of DL methods for open-world EEG decoding and identifies promising research directions to inspire future studies for EEG decoding in real-world applications.



Self-Supervised Representation Learning from Electroencephalography Signals

This work presents self-supervision strategies that can be used to learn informative representations from multivariate time series and demonstrates that this approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels.

Deep learning-based electroencephalography analysis: a systematic review

This work reviews 154 papers that apply DL to EEG, published between January 2010 and July 2018, and spanning different application domains such as epilepsy, sleep, brain–computer interfacing, and cognitive and affective monitoring, to extract trends and highlight interesting approaches from this large body of literature in order to inform future research and formulate recommendations.

Machine-learning-based diagnostics of EEG pathology

Deep learning with convolutional neural networks for decoding and visualization of EEG pathology

The ConvNets and visualization techniques used in this study constitute a next step towards clinically useful automated EEG diagnosis and establish a new baseline for future work on this topic.

Deep learning for EEG-based Motor Imagery classification: Accuracy-cost trade-off

The experimental results show that the optimization procedure improves accuracy in all models, and that CNN models with only one hidden convolutional layer can equal or slightly outperform a 6-layer Deep Belief Network.

Automated identification of abnormal adult EEGs

This work explores two baseline classification algorithms: k-Nearest Neighbor (kNN) and Random Forest Ensemble Learning (RF) and explores one of the early decisions made in this process - whether an EEG is normal or abnormal.

The Temple University Hospital EEG Data Corpus

A new corpus of EEG data is described, the TUH-EEG Corpus, which is an ongoing data collection effort that has recently released 14 years of clinical EEG data collected at Temple University Hospital and contains data from 22 subjects, mostly pediatric.

A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series

This work introduces here the first deep learning approach for sleep stage classification that learns end-to-end without computing spectrograms or extracting handcrafted features, that exploits all multivariate and multimodal polysomnography (PSG) signals (EEG, EMG, and EOG), and that can exploit the temporal context of each 30-s window of data.

Deep learning for EEG-based biometric recognition

Combining magnetoencephalography with magnetic resonance imaging enhances learning of surrogate-biomarkers

A multimodal model to robustly combine MEG, MRI and fMRI for prediction, focusing on age prediction as a surrogate biomarker in 674 subjects from the Cam-CAN dataset, is proposed.