Multi-Scale Spatio-Temporal Attention Network for Epileptic Seizure Prediction

• Published in: IEEE journal of biomedical and health informatics Vol. 29; no. 7; pp. 4784 - 4795
• Main Authors: Dong, Qiulei, Zhang, Han, Xiao, Jun, Sun, Jiayin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2025
• Subjects: Algorithms; Brain modeling; Computer vision; Convolution; Data mining; Electroencephalography; Electroencephalography (EEG) spectrogram; Electroencephalography - methods; epilepsy; Epilepsy - diagnosis; Epilepsy - physiopathology; Feature extraction; Humans; Long short term memory; multi-scale spatio-temporal attention; Neural Networks, Computer; seizure prediction; Seizures - diagnosis; Seizures - physiopathology; Signal Processing, Computer-Assisted; Spectrogram; Training; Transformers; vision transformer
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2025.3545265

Epilepticseizure prediction from electroencephalogram (EEG) data has attracted much attention in the clinical diagnosis and treatment of epilepsy. Most of the existing methods in literature extract either spatial or temporal features at a single scale from EEG data, however, their learned features are generally less discriminative since the EEG data is complex and severely noisy in general, leading to low-accuracy predictions. To address this problem, we propose a Multi-scale Spatio-temporal Attention Network to learn discriminative features for seizure prediction, called MSAN, which contains a backbone module, a spatial pyramid module, and a multi-scale sequential aggregation module. The backbone module is to extract initial spatial features from the input EEG spectrograms, and the pyramid module is introduced to learn multi-scale features from the initial features. Then by taking these multi-scale features as input temporal features, the sequential aggregation module employs multiple Long Short-Term Memory(LSTM) blocks to aggregate these features. In addition, a dual-loss function is introduced to alleviate the class imbalance problem. The proposed method achieves an average sensitivity of 96.27% with a mean false prediction rate of 0.00/h on the CHB-MIT dataset and an average sensitivity of 93.57% with a mean false prediction rate of 0.044/h on the Kaggle dataset. The comparative results demonstrate that the proposed method outperforms 10 state-of-the-art epileptic seizure prediction models.