SpaTeoGL: Spatiotemporal Graph Learning for Interpretable Seizure Onset Zone Analysis from Intracranial EEG

2026-02-12

AI Summary

Accurately localizing the seizure onset zone (SOZ) in intracranial electroencephalography (iEEG) requires modeling complex spatiotemporal dynamics. To address this, this work proposes SpaTeoGL, a novel framework that introduces joint spatiotemporal graph modeling into SOZ analysis for the first time. SpaTeoGL constructs window-level spatial graphs to capture inter-electrode relationships and builds a temporal graph across time windows based on structural similarity, enabling interpretable epileptic network modeling. The method leverages smooth graph signal processing and an alternating block coordinate descent algorithm with convergence guarantees. Evaluated on multicenter iEEG data, SpaTeoGL maintains competitive SOZ localization performance while significantly improving identification of non-SOZ regions, thereby revealing dynamic mechanisms underlying seizure initiation and propagation.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate localization of the seizure onset zone (SOZ) from intracranial EEG (iEEG) is essential for epilepsy surgery but is challenged by complex spatiotemporal seizure dynamics. We propose SpaTeoGL, a spatiotemporal graph learning framework for interpretable seizure network analysis. SpaTeoGL jointly learns window-level spatial graphs capturing interactions among iEEG electrodes and a temporal graph linking time windows based on similarity of their spatial structure. The method is formulated within a smooth graph signal processing framework and solved via an alternating block coordinate descent algorithm with convergence guarantees. Experiments on a multicenter iEEG dataset with successful surgical outcomes show that SpaTeoGL is competitive with a baseline based on horizontal visibility graphs and logistic regression, while improving non-SOZ identification and providing interpretable insights into seizure onset and propagation dynamics.

Problem

• seizure onset zone
• intracranial EEG
• spatiotemporal dynamics
• epilepsy surgery
• SOZ localization

Innovation

• spatiotemporal graph learning
• seizure onset zone
• interpretable AI
• graph signal processing
• intracranial EEG