Interpretable end to end Epileptic Seizure Detection via Linear and Nonlinear Filtering Networks

Epilepsy is a prevalent neurological disorder marked by recurrent, unpredictable seizures. Electroencephalogram (EEG)-based seizure detection has become a key focus in clinical research due to its potential for identifying abnormal brain activity patterns. However, most current approaches rely on single-modal feature analysis and struggle to disentangle the complex linear and nonlinear dynamics of EEG signals, limiting their clinical utility. To address this limitation, we propose a novel contrastive learning framework with linear and nonlinear filtering networks (CL-LNFNet) for interpretable seizure detection. CL-LNFNet enhances interpretability by tracing the full decision-making pathway from raw EEG signals to diagnostic outcomes. Through comparative analysis of feature evolution across six seizure types and non-seizure states, the model bridges the gap between the "black-box" nature of deep learning and the transparency required in clinical diagnostics. The framework first employs a recursive residual decomposition scheme to extract linear and nonlinear components using dual-branch decoupling networks. These features are then refined via two adaptive filtering networks equipped with feature selection gating mechanisms. A multi-scale convolutional module within a three-layer convolutional architecture hierarchically integrates the dual-stream outputs to improve classification performance. Furthermore, we introduce a hybrid learning strategy that combines supervised and self-supervised contrastive learning to enhance feature representation through the joint optimization of both loss functions. Experimental evaluations on both scalp and intracranial EEG datasets demonstrate that CL-LNFNet achieves over 95% accuracy in both cross-patient and specific-patient scenarios, outperforming existing state-of-the-art methods.