Efficient and Generalizable Cross-patient Epileptic Seizure Detection through a Spiking Neural Network

Zongpeng Zhang, Mingqing Xiao, Taoyun Ji, Yuwu Jiang, Tong Lin, Xiao-Hua Zhou, Zhouchen Lin

Abstract:

Epilepsy is a global chronic disease that brings pain and inconvenience to patients, and electroencephalogram (EEG) is the main analytical tool. For clinical aid which can be applied to any patient, automatic cross-patient epilepsy seizure detection algorithm is of great significance. Spiking neural networks (SNNs) are inspired by modeling biological neurons and are energy-efficient on neuromorphic hardware, which can be expected to better handle brain signals and benefit low-power real-world applications. However, automatic epilepsy seizure detection rarely considers SNNs. In this paper, we explore SNNs for cross-patient seizure detection and discover that SNNs can achieve comparable state-of-the-art performance or even better than artificial neural networks (ANNs). We propose an EEG-based spiking neural network (EESNN) with the recurrent spiking convolution structure, which may better take advantage of temporal and biological characteristics in EEG signals.
We extensively evaluate the performance of different SNN structures, training methods and time settings, which builds a solid basis for understanding and evaluation of SNNs in seizure detection. Moreover, we show that our EESNN model can achieve energy reduction by several orders of magnitude compared with ANNs according to the theoretical estimation. These results show the potential for building high-performance, low-power neuromorphic systems for seizure detection, and also broaden real-world application scenarios of SNNs.