EpiLENS: Patient-Relative Epileptogenic Zone Localization from Multi-Center Intracranial EEG

2026-08-02

AI Summary

This work addresses the challenge of inaccurate epileptogenic zone localization in drug-resistant epilepsy, which arises from patient heterogeneity, seizure variability, electrode placement differences, and multi-center discrepancies. To this end, the authors propose EpiLENS, a novel framework introducing a patient-relative localization paradigm. EpiLENS integrates two complementary branches: PRQ-Net, which references individual electrophysiological baselines, and BCR-Net, which emphasizes boundary coverage. During inference, their evidence is asymmetrically fused via a conservative dual-evidence localization (CDEL) strategy. Key innovations—including intra-patient baseline normalization, lower-tail seizure aggregation, and boundary coverage ranking—substantially enhance generalization across seizures and centers. Evaluated on a heterogeneous four-center intracranial EEG cohort, EpiLENS significantly outperforms conventional feature-based methods and end-to-end neural network baselines, maintaining robust performance under class imbalance and annotation noise.

Abstract

Drug-resistant epilepsy remains a major clinical challenge, as successful neurosurgery depends critically on accurate epileptogenic zone (EZ) localization accounting for substantial variability across patients, seizures, implantation layouts, recording systems and clinical centers. Existing intracranial electroencephalogram (iEEG) methods typically rely on channel-wise classifiers trained globally, which often obscure patient-specific electrophysiological abnormalities and exhibit instability under severe class imbalance and noisy clinical annotations. To address these limitations, we present EpiLENS, a primary-guided asymmetric dual-branch framework for patient-relative epileptogenic localization. Its localization strategy, Conservative Dual-Evidence Localization (CDEL), asymmetrically combines independently trained but complementary branches at inference: the Patient-Relative Quantile Network (PRQ-Net), which captures seizure-consistent deviations from each patient's internal electrophysiological baseline, and the Boundary-Coverage Ranking Network (BCR-Net), which emphasizes ambiguous epileptogenic zone or non-epileptogenic zone boundaries and recovery of the patient-specific epileptogenic set. CDEL retains PRQ-Net as the primary branch while incorporating complementary patient-wise ranking evidence from BCR-Net. Experiments on a heterogeneous four-center cohort demonstrate improved balanced localization over classical feature-based and raw-iEEG neural baselines, while component ablations and within-patient permutation analyses support the contributions of patient-relative normalization, lower-tail seizure aggregation, and boundary-coverage ranking. Cross-seizure and leave-one-center-out generalization experiments further confirm that the proposed patient-relative evidence remains robust across repeated recordings and transfers effectively to unseen clinical centers.

Problem

• epileptogenic zone localization
• patient-relative
• intracranial EEG
• drug-resistant epilepsy
• multi-center

Innovation

• patient-relative localization
• asymmetric dual-branch framework
• Conservative Dual-Evidence Localization (CDEL)
• intracranial EEG
• epileptogenic zone