Epileptic Seizure Risk Assessment by Multi-Channel Imaging of the EEG

TL;DR

This study proposes a CNN-based method using multi-channel EEG images to predict epileptic seizures, showing improved sensitivity and false positive rates, serving as a promising proof of concept for seizure prediction.

Contribution

It introduces a novel approach of using the likelihood from CNN softmax layers on EEG images for seizure prediction, enhancing detection metrics.

Findings

Higher sensitivity achieved by analyzing likelihood thresholds

Optimal threshold varies across patients, above 50% for some

Method shows promise but requires further testing in new seizures

Abstract

Refractory epileptic patients can suffer a seizure at any moment. Seizure prediction would substantially improve their lives. In this work, based on scalp EEG and its transformation into images, the likelihood of an epileptic seizure occurring at any moment is computed using an average of the softmax layer output (the likelihood) of a CNN, instead of the output of the classification layer. Results show that by analyzing the likelihood and thresholding it, prediction has higher sensitivity or a lower FPR/h. The best threshold for the likelihood was higher than 50% for 5 patients, and was lower for the remaining 36. However, more testing is needed, especially in new seizures, to better assess the real performance of this method. This work is a proof of concept with a positive outlook.