Long-Term EEG Partitioning for Seizure Onset Detection

TL;DR

This paper introduces SODor, a two-stage deep learning framework that models long-term EEG dependencies for improved seizure onset detection through subsequence clustering.

Contribution

It presents a novel task formulation and clustering-based approach for explicit seizure onset detection in EEG sequences, enhancing existing classification methods.

Findings

Achieves 5-11% classification improvements over baselines.

Accurately detects seizure onsets in multiple datasets.

Corrects misclassifications effectively.

Abstract

Deep learning models have recently shown great success in classifying epileptic patients using EEG recordings. Unfortunately, classification-based methods lack a sound mechanism to detect the onset of seizure events. In this work, we propose a two-stage framework, SODor, that explicitly models seizure onset through a novel task formulation of subsequence clustering. Given an EEG sequence, the framework first learns a set of second-level embeddings with label supervision. It then employs model-based clustering to explicitly capture long-term temporal dependencies in EEG sequences and identify meaningful subsequences. Epochs within a subsequence share a common cluster assignment (normal or seizure), with cluster or state transitions representing successful onset detections. Extensive experiments on three datasets demonstrate that our method can correct misclassifications, achieving 5\%-11\% classification improvements over other baselines and accurately detecting seizure onsets.