Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy

Thi Kieu Khanh Ho; Thomas Lai; Petr Klimes; Jan Cimbalnik; Martin Pail; Milan Brazdil; Birgit Frauscher; Narges Armanfard

cs.LGJun 21, 2026

Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy

Authors: Thi Kieu Khanh Ho, Thomas Lai, Petr Klimes, Jan Cimbalnik, Martin Pail, Milan Brazdil, Birgit Frauscher, Narges Armanfard

Organizations: Department of Electrical and Computer Engineering, McGill University, Montr´eal, Quebec, Canada. · Mila-Quebec AI Institute, Montr´eal, Quebec, Canada. · Montreal Neurological Institute and Hospital, McGill University, Montr´eal, Quebec, Canada. · Institute of Scientific Instruments, The Czech Academy of Sciences, Brno, Czech Republic. · Analytical Neurophysiology Lab, Department of Neurology, Duke University Medical Center, Durham, NC, USA. · Brno Epilepsy Center, Department of Neurology, St Anne’s University Hospital, Brno, Czech Republic. · Faculty of Medicine, Masaryk University, Brno, Czech Republic. · Department of Biomedical Engineering, Duke Pratt School of Engineering, Durham, NC, USA.

Abstract

Accurate identification of the epileptogenic zone (EZ) is essential for seizure freedom after resective surgery in drug-resistant epilepsy, yet seizure freedom rates remain below 50%. We developed EpiiSLM, a dual foundation model system for EZ identification with stereo-electroencephalography (sEEG), by training a signal foundation model on 104,990 minutes of sEEG recordings from the Montreal Neurological Institute & Hospital, while leveraging all recordings regardless of surgical outcome and anchoring EZ biomarker extraction on non-epileptic signals. A language foundation model then integrates sEEG-derived outputs with multimodal clinical information to produce interpretable predictions. Under leave-one-patient-out evaluation, EpiiSLM achieved 0.978 contact-level positive predictive value (PPV), outperforming the seizure onset zone(SOZ)-as-EZ baseline by 15.1% (p < 0.05), and 100% region-level accuracy; on an external dataset, EpiiSLM achieved 0.857 contact-level PPV. EpiiSLM requires only one night of interictal sleep data, suggesting potential to reduce invasive sEEG monitoring duration and improve surgical outcomes.

Explore similar work

Multimodal Pretraining for Generalizable EEG Representation Learning
Jul 23, 2026Targol Bakhtiarvand, Jugal Kalita, Adham AtyabiElectroencephalography Foundation Models Interictal Epileptiform Discharges
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
Jul 13, 2026Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri +2Interictal Epileptiform Discharges Electroencephalography Spatial Super-Resolution
EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction
Jun 1, 2026Vigneshwar Hariharan, Chithra Reghuvaran, Arlene John +4Interictal Epileptiform Discharges Fusion

Jul 23, 2026 · cs.AIJ/K move · Enter open · S save

Multimodal Pretraining for Generalizable EEG Representation Learning

Targol Bakhtiarvand, Jugal Kalita, Adham Atyabi

Department of Computer Science, University of Colorado Colorado Springs, Colorado Springs, CO, USA

Electroencephalography (EEG) models used for epilepsy are often limited to specific datasets and tasks. This limited approach can make it challenging to apply these models across different datasets or in various situations. However, recent studies in foundation models and self-supervised learning suggest that an adaptable EEG backbone could support a range of EEG related tasks. In this study, we have developed a multimodal EEG foundation model that combines a raw signal encoder based on the Mamba architecture, a Vision Transformer (ViT)-style encoder for time-frequency data, and a lightweight encoder for text, all within a shared embedding space. The pretraining process relies on several innovative techniques, such as masked modeling, cross-view contrastive alignment, and temporal consistency losses. These methods are designed to create rich, seizure-relevant representations without requiring labeled data. To assess the efficacy and generalization of our pretrained model, we fine-tuned it on the canonical CHB-MIT seizure detection benchmark and additional seizure detection datasets, and conducted extensive experiments comparing different model variants. On the standard CHB-MIT split, our best single model achieved an AUROC of 0.874, and an ensemble variant reached 0.878 AUROC, representing state-of-the-art performance on this benchmark. In addition to standard train-test splits, we evaluated performance under a leave-one-subject-out (LOSO) protocol, which is rarely reported in prior EEG seizure modeling work and highlights the difficulty of patient-independent seizure detection, with a mean LOSO balanced accuracy of 0.558 across 19 subjects. Across datasets and evaluation settings, our multimodal foundation model enabled robust seizure detection and straightforward adaptation to new seizure detection scenarios, while also supporting interpretable seizure localization.

Electroencephalography Foundation Models Interictal Epileptiform Discharges Representation Learning Multimodal Learning Vision Encoders

Open paper Ask about it PDF

Abstract

Explore similar work

Multimodal Pretraining for Generalizable EEG Representation Learning

DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations

EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction