Deep Classification of Epileptic Signals

TL;DR

This paper introduces a deep learning approach using LSTM networks for automatic classification of epileptic EEG signals, achieving high accuracy without manual feature engineering, thus advancing clinical diagnosis tools.

Contribution

The study presents a novel LSTM-based deep learning method that automatically learns features from raw EEG data for epileptic seizure detection, reducing the need for pre-processing and complex feature design.

Findings

Achieved 95.54% validation accuracy on a public EEG dataset

Demonstrated that simple LSTM architectures are effective for seizure classification

Validated the approach's potential for practical clinical applications

Abstract

Electrophysiological observation plays a major role in epilepsy evaluation. However, human interpretation of brain signals is subjective and prone to misdiagnosis. Automating this process, especially seizure detection relying on scalp-based Electroencephalography (EEG) and intracranial EEG, has been the focus of research over recent decades. Nevertheless, its numerous challenges have inhibited a definitive solution. Inspired by recent advances in deep learning, we propose a new classification approach for EEG time series based on Recurrent Neural Networks (RNNs) via the use of Long-Short Term Memory (LSTM) networks. The proposed deep network effectively learns and models discriminative temporal patterns from EEG sequential data. Especially, the features are automatically discovered from the raw EEG data without any pre-processing step, eliminating humans from laborious feature design task. We also show that, in the epilepsy scenario, simple architectures can achieve competitive performance. Using simple architectures significantly benefits in the practical scenario considering their low computation complexity and reduced requirement for large training datasets. Using a public dataset, a multi-fold cross-validation scheme exhibited an average validation accuracy of 95.54\% and an average AUC of 0.9582 of the ROC curve among all sets defined in the experiment. This work reinforces the benefits of deep learning to be further attended in clinical applications and neuroscientific research.