Graph Neural Networks in Epilepsy Surgery

conference paper

English

Epilepsy surgery presents a viable treatment option for patients with drug-resistant epilepsy, necessitating precise localization of the epileptogenic zone (EZ) for optimal outcomes. As the limitations of currently used localization methods lead to a seizure-free postsurgical outcome only in about 60% of cases, this study introduces a novel approach to EZ localization by leveraging Graph Neural Networks (GNNs) for the analysis of interictal stereoelectroencephalography (SEEG) data. A GraphSAGE-based model for identifying resected seizure-onset zone (SOZ) electrode contacts was applied to a clinical dataset comprising 17 patients from two institutions. This study uniquely focuses on the use of interictal SEEG recordings, aiming to streamline the presurgical monitoring process and minimize risks and costs associated with prolonged SEEG monitoring. Through this innovative approach, the GNN model demonstrated promising results, achieving an Area Under the Receiver Operating Characteristic (AUROC) score of 0.830 and an Area Under the Precision-Recall Curve (AUPRC) of 0.432. These outcomes along with the potential of GNNs in leveraging the patient-specific electrode placement highlight their potential in enhancing the accuracy of EZ localization in drug-resistant epilepsy patients.

Graph neural networks, deep learning, epilepsy, intracranial EEG, epileptogenic zone, seizure-onset zone, interictal biomarkers

HRTOŇOVÁ, V.; FILIPENSKÁ, M.; KLIMEŠ, P.

23. 4. 2024

Brno University of Technology, Faculty of Electrical Engineering and Communication

Brno

978-80-214-6230-4

Proceedings II of the 30th Conference STUDENT EEICT 2024: Selected papers

1

57

60

4

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2024_sbornik_2.pdf