Epileptic Seizure Prediction: A Semi-Dilated Convolutional Neural Network Architecture

TL;DR

This paper introduces a semi-dilated convolutional neural network architecture that effectively predicts epileptic seizures from EEG scalograms by capturing long-range temporal dependencies while preserving spectral resolution.

Contribution

The work presents a novel semi-dilated convolutional module and architecture tailored for EEG scalogram analysis, improving seizure prediction accuracy over existing methods.

Findings

Achieved seizure prediction sensitivities of 88.45% and 89.52%.

Outperformed state-of-the-art seizure prediction methods.

Effectively captured long-range temporal features in EEG data.

Abstract

Accurate prediction of epileptic seizures has remained elusive, despite the many advances in machine learning and time-series classification. In this work, we develop a convolutional network module that exploits Electroencephalogram (EEG) scalograms to distinguish between the pre-seizure and normal brain activities. Since these scalograms have rectangular image shapes with many more temporal bins than spectral bins, the presented module uses "semi-dilated convolutions" to create a proportional non-square receptive field. The proposed semi-dilated convolutions support exponential expansion of the receptive field over the long dimension (image width, i.e. time) while maintaining high resolution over the short dimension (image height, i.e., frequency). The proposed architecture comprises a set of co-operative semi-dilated convolutional blocks, each block has a stack of parallel semi-dilated convolutional modules with different dilation rates. Results show that our proposed solution outperforms the state-of-the-art methods, achieving seizure prediction sensitivity scores of 88.45% and 89.52% for the American Epilepsy Society and Melbourne University EEG datasets, respectively.