VAEEG: Variational auto-encoder for extracting EEG representation
Tong Zhao,
Yi Cui,
Taoyun Ji,
Jiejian Luo,
Wenling Li,
Jun Jiang,
Zaifen Gao,
Wenguang Hu,
Yuxiang Yan,
Yuwu Jiang,
Bo Hong
Affiliations
Tong Zhao
Gnosis Neurodynamics Co. Ltd, Beijing, China; School of Biomedical Engineering, Tsinghua University, Beijing, China
Yi Cui
Gnosis Neurodynamics Co. Ltd, Beijing, China
Taoyun Ji
Department of Pediatrics, Peking University First Hospital, Beijing, China
Jiejian Luo
Gnosis Neurodynamics Co. Ltd, Beijing, China; School of Biomedical Engineering, Tsinghua University, Beijing, China
Wenling Li
Department of Neurosurgery, The Second Hospital of Hebei Medical University, Shijiazhuang, Hebei, China
Jun Jiang
Department of Electrophysiology, Tongji Medical College, Wuhan Children's Hospital, Huazhong University of Science & Technology, Wuhan, China
Zaifen Gao
Department of Epilepsy Center, Children's Hospital Affiliated to Shandong University, Jinan Children's Hospital, Jinan, ShanDong, China
Wenguang Hu
Department of Pediatric Neurology, School of Medicine, Chengdu Women' and Children's Central Hospital, University of Electronic Science and Technology of China, Chengdu, Sichuan, China
The electroencephalogram (EEG) exhibits characteristics of complexity and strong randomness. Existing deep learning models for EEG typically target specific objectives and datasets, with their scalability constrained by the size of the dataset, resulting in limited perceptual and generalization abilities. In order to obtain more intuitive, concise, and useful representations of brain activity, we constructed a reconstruction-based self-supervised learning model for EEG based on Variational Autoencoder (VAE) with separate frequency bands, termed variational auto-encoder for EEG (VAEEG). VAEEG achieved outstanding reconstruction performance. Furthermore, we validated the efficacy of the latent representations in three clinical tasks concerning pediatric brain development, epileptic seizure, and sleep stage classification. We discovered that certain latent features: 1) correlate with adolescent brain developmental changes; 2) exhibit significant distinctions in the distribution between epileptic seizures and background activity; 3) show significant variations across different sleep cycles. In corresponding downstream fitting or classification tasks, models constructed based on the representations extracted by VAEEG demonstrated superior performance. Our model can extract effective features from complex EEG signals, serving as an early feature extractor for downstream classification tasks. This reduces the amount of data required for downstream tasks, simplifies the complexity of downstream models, and streamlines the training process.
