AI-Driven SEEG Channel Ranking for Epileptogenic Zone Localization

TL;DR

This paper introduces a machine learning method using XGBoost and SHAP to rank SEEG channels for epileptogenic zone localization, improving efficiency and explainability in pre-surgical evaluation.

Contribution

It presents a novel approach combining clinician input and computational analysis to automatically rank impactful SEEG channels for epilepsy surgery planning.

Findings

Validated on data from five patients with promising accuracy

Enhanced channel ranking with explainability via SHAP scores

Incorporated channel extension strategy to identify additional zones

Abstract

Stereo-electroencephalography (SEEG) is an invasive technique to implant depth electrodes and collect data for pre-surgery evaluation. Visual inspection of signals recorded from hundreds of channels is time consuming and inefficient. We propose a machine learning approach to rank the impactful channels by incorporating clinician's selection and computational finding. A classification model using XGBoost is trained to learn the discriminative features of each channel during ictal periods. Then, the SHapley Additive exPlanations (SHAP) scoring is utilized to rank SEEG channels based on their contribution to seizures. A channel extension strategy is also incorporated to expand the search space and identify suspicious epileptogenic zones beyond those selected by clinicians. For validation, SEEG data for five patients were analyzed showing promising results in terms of accuracy, consistency, and explainability.