A self-attention model for cross-subject seizure detection

• Published in: Computers in biology and medicine Vol. 165; p. 107427
• Main Authors: Abdallah, Tala, Jrad, Nisrine, Abdallah, Fahed, Humeau-Heurtier, Anne, Van Bogaert, Patrick
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.10.2023; Elsevier Limited; Elsevier
• Subjects: Artificial neural networks; Coders; Convolutional neural network (CNN); Convulsions & seizures; Deep learning; Deep learning (DL); EEG; Electroencephalography; Electroencephalography (EEG); Engineering Sciences; Epilepsy; Epileptic seizure recognition; Internal Medicine; Long short-term memory; Long short-term memory (LSTM); Machine learning; Neural networks; Neurological diseases; Other; Seizures; Self-attention (SAT); Signal and Image processing; Signal processing; Self-attention (SAT); Electroencephalography (EEG); Convolutional neural network (CNN); Epileptic seizure recognition; Deep learning (DL); Long short-term memory (LSTM)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.107427

Epilepsy is a neurological disorder characterized by recurring seizures, detected by electroencephalography (EEG). EEG signals can be detected by manual time-consuming analysis and recently by automatic detection. The latter poses a significant challenge due to the high dimensional and non-stationary nature of EEG signals. Recently, deep learning (DL) techniques have emerged as valuable tools for seizure detection. In this study, a novel data-driven model based on DL, incorporating a self-attention mechanism (SAT), is proposed. One notable advantage of the proposed method is its simplicity in application, as the raw signal data is directly fed into the suggested network without requiring expertise in signal processing. The model leverages a one-dimensional convolutional neural network (CNN) to extract relevant features from EEG signals. These features are then passed through a long short-term memory (LSTM) module to benefit from its memory capabilities, along with a SAT mechanism. The key contribution of this paper lies in the addition of the SAT layer to the LSTM encoder, enabling enhanced exploration of the latent mapping during the encoding step. Cross-subject experiments revealed good performance of this approach with F1-score of 97.8% and 92.7% for binary and five-class epileptic seizure recognition tasks, respectively, on the public UCI dataset, and 97.9% on the CHB-MIT database, surpassing state-of-the-art DL performance. Besides, the proposed method exhibits robustness to inter-subject variability. •A hybrid method, CNN-LSTM-SAT, is proposed for epileptic seizure detection.•The proposed method was validated on two public online datasets.•The model’s robustness to inter-subject variability is also confirmed.•The performance of CNN-LSTM-SAT is verified by comparison with recent works.•The inclusion of a SAT layer overcomes the limitation observed in previous models.