Skip to content
Open access

Localizing the epileptogenic zone in drug-resistant epilepsy based on ictal SEEG high-resolution time-frequency representation

Aug 2026 · Frontiers in Neuroscience · Vol 20 · 0 citations · 70 references
Medicine

TL;DR

An automated EZ localization framework leveraging ictal SEEG high-resolution time-frequency representation (TFR) and convolutional neural network (CNN) provides a reliable and objective tool for clinical EZ localization, and holds substantial optimization potential via integration of complex architectures such as Transformer and Mamba-based models.

Abstract

Introduction Drug-resistant epilepsy (DRE) presents a critical clinical challenge, and accurate epileptogenic zone (EZ) localization is essential for successful surgical intervention. Stereoelectroencephalography (SEEG) is widely applied in clinical practice, but conventional visual inspection and high-frequency oscillations (HFOs) suffer from low efficiency, poor reproducibility, and insufficient representation of complex neural dynamics, failing to improve postsurgical seizure-free rates substantially. To address the limitations, we developed an automated EZ localization framework leveraging ictal SEEG high-resolution time-frequency representation (TFR) and convolutional neural network (CNN). Methods Twenty three adult individuals with DRE who achieved Engel Class I surgical outcomes were enrolled in this study. The TFRs of ictal SEEG (0.5–500 Hz) were generated using Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), and Superlet Transform, then were classified by VGG16/19 and ResNet-18/34/50. Results Under subject-independent cross-validation, the optimal HFO-based method achieved an accuracy of 66.10 ± 1.40%, an F1-score of 49.49 ± 2.48% and an AUC of 67.95% ± 2.35%. By comparison, Superlets-VGG19 model achieved significantly better performance: an accuracy of 80.46 ± 4.61%, an F1-score of 79.52 ± 6.88% and an AUC of 80.06 ± 5.23%. Notably, the framework exhibited superior performance in the radiofrequency thermocoagulation (RFTC) sub-cohort, with an accuracy of 82.31 ± 3.41%, an F1-score of 82.56 ± 4.62%, and an AUC of 82.85 ± 3.80%. Discussion The proposed framework outperforms conventional HFO-based baselines and provides a reliable and objective tool for clinical EZ localization, and holds substantial optimization potential via integration of complex architectures such as Transformer and Mamba-based models.

Read PDF

Similar papers

Oct 2026

Cross-Subject Localization of Epileptogenic Zone for Drug-Resistant Epilepsy Based on the Causal Brain Network.

OBJECTIVE While neurosurgical treatment is the primary intervention for Drug-resistant epilepsy (DRE) patients, its success rate is limited to approximately 60%. Precise localization of epileptogenic zone (EZ) is a critical factor for surgical success. This study aims to achieve cross-subject localization of the EZ in...

Ya-Lin Wang, Wei-Xin Kong, Ya-Qing Liu 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
Open access Sep 2026

Non-invasive preoperative prediction of surgical outcomes in drug-resistant epilepsy using seizure-related EEG network dynamics

Stereoelectroencephalography (SEEG)-guided radiofrequency thermocoagulation (RF-TC) has emerged as a minimally invasive treatment option for selected patients with drug-resistant epilepsy (DRE). However, its overall therapeutic efficacy remains suboptimal, with seizure-free rates typically falling below 70%. To facilit...

R. Feng, Q. Luo, Dan-Ni Yang et al. · 0 citations
Review Open access Aug 2026

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

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.

H. Kumar, D. Martínez, G. P et al. · 0 citations
Open access Sep 2026

How to Recognize and Manage Missing Key Electrodes in Defining the Epileptogenic Zone

Identifying and localizing the epileptogenic zone (EZ) is the cornerstone of successful epilepsy surgery, as it directly determines surgical efficacy and patient outcomes. Stereoelectroencephalography (SEEG) has emerged as a transformative tool for pinpointing the EZ, offering precise 3-dimensional recordings of seizur...

Hussam Shaker, S. Médina Villalon, J. González-Martínez 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.