Geometric representations of brain networks can predict the surgery outcome in temporal lobe epilepsy

TL;DR

This study presents a novel non-Euclidean network geometry-based biomarker derived from MRI data that effectively predicts surgical outcomes in temporal lobe epilepsy with high accuracy.

Contribution

It introduces hyperbolic embeddings of brain networks as a new approach for outcome prediction in epilepsy surgery, highlighting regions in the contralateral hemisphere as biomarkers.

Findings

Achieved AUC of 0.87 in outcome prediction

Identified contralateral hemisphere regions as key biomarkers

Demonstrated the effectiveness of non-Euclidean network analysis

Abstract

Epilepsy surgery, particularly for temporal lobe epilepsy (TLE), remains a vital treatment option for patients with drug-resistant seizures. However, accurately predicting surgical outcomes remains a significant challenge. This study introduces a novel biomarker derived from brain connectivity, analyzed using non-Euclidean network geometry, to predict the surgery outcome in TLE. Using structural and diffusion magnetic resonance imaging (MRI) data from 51 patients, we examined differences in structural connectivity networks associated to surgical outcomes. Our approach uniquely utilized hyperbolic embeddings of pre- and post-surgery brain networks, successfully distinguishing patients with favorable outcomes from those with poor outcomes. Notably, the method identified regions in the contralateral hemisphere relative to the epileptogenic zone, whose connectivity patterns emerged as a potential biomarker for favorable surgical outcomes. The prediction model achieves an area under the curve (AUC) of 0.87 and a balanced accuracy of 0.81. These results underscore the predictive capability of our model and its effectiveness in individual outcome forecasting based on structural network changes. Our findings highlight the value of non-Euclidean representation of brain networks in gaining deeper insights into connectivity alterations in epilepsy, and advancing personalized prediction of surgical outcomes in TLE.