The interpretable deep learning framework and validation for seizure detection in pediatric electroencephalography:...

This study proposes an interpretable deep learning framework and compares the two novel models. A fully convolutional network with squeeze-and-excitation modules (SE-FCN) is designed to enhance spatial sensitivity and retain temporal resolution. In addition, a transformer-based model (TransNet) is developed to capture temporal and channel-wise dependencies via self-attention. These two models output channel saliency weights to the EEG electrode space and generate heatmaps for inferring potential epileptogenic zones. Deep learning primarily adopts convolutional neural networks (CNNs) or sequence generation networks (SGNs) and faces the limitations. For instance, CNN-based models often lack hierarchical modeling and fail to quantify channel-wise contributions, hindering spatial localization. SGN-based models struggle to capture complex spatiotemporal dependencies and typically lack adaptive attention tailored to electroencephalography (EEG) characters. Epileptic seizure detection is vital for effective clinical intervention and existing methods operated as black boxes, limiting clinical interpretability. This study evaluates the models on the CHB-MIT pediatric EEG dataset using a subject-independent cross-validation protocol. SE-FCN achieves an AUC of 0.89 and accuracy of 86.7 %, while TransNet achieves an AUC of 0.92 and accuracy of 86.4 %. Saliency maps from both models demonstrate high consistency and enable categorization of 22 patients into five groups based on inferred seizure origins.