Skip to content
Review Open access

Seizure Onset Zone Localization in Drug-Resistant Epilepsy Using Self-Supervised Learning on Stereo-EEG

Aug 2026 · medRxiv · 0 citations
Medicine

TL;DR

A self-supervised CNN--Transformer encoder that learns contact-level peri-ictal representations from 60-second superlet spectrograms through InfoNCE contrastive pretraining is developed that augments expert SEEG review and surfaces candidate contacts for re-review in poor-outcome cases.

Abstract

Accurate localization of the seizure onset zone (SOZ) is a central determinant of surgical outcome in drug-resistant focal epilepsy, yet identifying it from stereo-electroencephalography (SEEG) remains a slow, subjective visual task. We developed a self-supervised CNN--Transformer encoder (CSOPE-Net; Contrastive Seizure-Onset Pattern Encoder) that learns contact-level peri-ictal representations from 60-second superlet spectrograms through InfoNCE contrastive pretraining. We evaluated this representation as a framework for SOZ localization, seizure-onset phenotype clustering, and identification of clinically labeled non-SOZ contacts with SOZ-like morphology in poor-outcome patients. Across 149 patients partitioned a priori into a development cohort (n=119) and an independent held-out cohort (n=30; 18 good-outcome subjects for classification validation and 12 poor-outcome subjects for SOZ-proximal replication), the model achieved aggregate ROC-AUC 0.854 under leave-one-subject-out cross-validation, 0.935 on held-out good-outcome subjects, and 0.822 on an independent external cohort (HUP iEEG dataset), with consistent performance across patients. The learned representation organized seizure onsets into reproducible phenotype families and, in poor-outcome patients, flagged clinically labeled non-SOZ contacts whose spectrotemporal features resembled those of high-confidence SOZ contacts. This signal reproduced in held-out data, and in a blinded re-review three experts endorsed these contacts as showing ictal-onset morphology at approximately 15-fold higher odds than matched non-SOZ controls. This framework augments expert SEEG review and surfaces candidate contacts for re-review in poor-outcome cases.

Read PDF

Similar papers

Open access Oct 2026

Weakly Supervised Multiple-Instance Learning for Seizure Onset Zone Identification

Accurate localization of the seizure onset zone (SOZ) is essential for planning resection or ablation in patients with focal drug-resistant epilepsy (DRE). However, the true SOZ cannot be directly observed during clinical evaluation, so precise electrode-level annotations are rarely available. To address this limitatio...

J. Mao, A. Le Sage, L. Camarillo-Rodriguez et al. · 0 citations
Open access Aug 2026

Patient-independent seizure onset zone localization with generalizable feature learning and multi-task supervision.

Most existing ictal stereoelectroencephalography (SEEG)-based seizure onset zone (SOZ) localization methods rely on patient-specific training, limiting their clinical applicability due to the scarcity of seizure recordings and substantial inter-patient variability. Consequently, robust patient-independent SOZ localizat...

Jin-Jie Guo, Tao Feng, Yiping Wang et al. · 0 citations
Aug 2026

Patient-Specific Non-Invasive Epileptogenic Zone Localization via High-Resolution Time-Frequency Representations and CNN Deep Learning.

An automated non-invasive EZ localization framework that integrates scalp EEG source imaging, high-resolution time-frequency analysis, and deep learning is developed that enables accurate personalized pre-surgical EZ map ping to optimize SEEG implantation planning.

Ya-Lin Wang, Wenbin Yuan, Ya-Qing Liu et al. · 2 citations

Using single pulse electric stimulation and deep learning methods to identify the seizure onset zone

A hybrid convolutional–transformer neural network that classifies whether individual recording contacts lie within the seizure onset zone using the first 100 ms of stimulation-evoked responses indicates that stimulation-evoked responses can contribute to seizure onset zone localization without requiring spontaneous sei...

Chandra Varun Reddy Bajepally · 0 citations
Open access Aug 2026

Machine-Learning-Based Localization of Cortical Hyperexcitability Zones from Background EEG Activity in Epilepsy

These findings establish background EEG activity as a promising clinically relevant biomarker for focal epilepsy diagnosis and highlight the feasibility of developing automated, expert-independent localization tools, addressing a critical unmet need in clinical neurophysiology.

A. E. Malkov, A. Lebedeva, Artem A. Sharkov et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.