Learning Robust Global-Local Representation From EEG for Neural Epilepsy Detection

Abstract

Epilepsy is a life-threatening and challenging neurological disorder, and applying electroencephalogram (EEG) is a commonly used clinical approach for its detection. Neuropsychological research indicates that epilepsy seizure is highly associated with distinct ranges of temporal EEG patterns. Although previous attempts to automatically detect epilepsy have achieved high classification performance, one crucial challenge still remains: How to effectively learn the robust global-local representation associated with epilepsy in the signals? To address the above challenge, we propose GlepNet, a novel architecture for automatic EEG epilepsy detection. We interleave temporal convolution model together with the muti-head attention mechanism within the GlepNet’s encoder blocks to jointly capture the interlaced epilepsy seizure local and global features in EEG signals. Meanwhile, the interpretable method, Grad-CAM, is applied to visually confirm that the GlepNet acquires the ability to accord significant weight to EEG segments containing epileptiform abnormalities like spike-wave complexes. Specifically, the Grad-CAM heatmaps are generated by backpropagating the gradients from the encoder blocks to highlight the epilepsy seizure-related parts. Extensive experiments show the superiority of the GlepNet over state-ofthe-art methods on multiple EEG epilepsy datasets. The code will soon be open-sourced on GitHub.