Long-Term EEG Partitioning for Seizure Onset Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zheng, Matsubara, Yasuko, Sakurai, Yasushi, Sun, Jimeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915178237394944
author Chen, Zheng
Matsubara, Yasuko
Sakurai, Yasushi
Sun, Jimeng
author_facet Chen, Zheng
Matsubara, Yasuko
Sakurai, Yasushi
Sun, Jimeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15598
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Long-Term EEG Partitioning for Seizure Onset Detection
Chen, Zheng
Matsubara, Yasuko
Sakurai, Yasushi
Sun, Jimeng
Machine Learning
Artificial Intelligence
Signal Processing
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.
title Long-Term EEG Partitioning for Seizure Onset Detection
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2412.15598