Merging Deep Learning with Expert Knowledge for Seizure Onset Zone localization from rs-fMRI in Pediatric Pharmaco Resistant Epilepsy

TL;DR

This paper introduces DeepXSOZ, a hybrid deep learning and expert knowledge-based method for localizing seizure onset zones in pediatric epilepsy using rs-fMRI, improving accuracy and reducing expert workload.

Contribution

DeepXSOZ combines deep learning spatial features with expert rule-based knowledge, enhancing SOZ localization accuracy and efficiency in pediatric PRE pre-surgical screening.

Findings

Achieves 89.79% sensitivity and 93.6% precision in localization.

Reduces expert sorting effort by 6.7 times.

Enables rs-fMRI as a cost-effective outpatient screening tool.

Abstract

Surgical disconnection of Seizure Onset Zones (SOZs) at an early age is an effective treatment for Pharmaco-Resistant Epilepsy (PRE). Pre-surgical localization of SOZs with intra-cranial EEG (iEEG) requires safe and effective depth electrode placement. Resting-state functional Magnetic Resonance Imaging (rs-fMRI) combined with signal decoupling using independent component (IC) analysis has shown promising SOZ localization capability that guides iEEG lead placement. However, SOZ ICs identification requires manual expert sorting of 100s of ICs per patient by the surgical team which limits the reproducibility and availability of this pre-surgical screening. Automated approaches for SOZ IC identification using rs-fMRI may use deep learning (DL) that encodes intricacies of brain networks from scarcely available pediatric data but has low precision, or shallow learning (SL) expert rule-based inference approaches that are incapable of encoding the full spectrum of spatial features. This paper proposes DeepXSOZ that exploits the synergy between DL based spatial feature and SL based expert knowledge encoding to overcome performance drawbacks of these strategies applied in isolation. DeepXSOZ is an expert-in-the-loop IC sorting technique that a) can be configured to either significantly reduce expert sorting workload or operate with high sensitivity based on expertise of the surgical team and b) can potentially enable the usage of rs-fMRI as a low cost outpatient pre-surgical screening tool. Comparison with state-of-art on 52 children with PRE shows that DeepXSOZ achieves sensitivity of 89.79%, precision of 93.6% and accuracy of 84.6%, and reduces sorting effort by 6.7-fold. Knowledge level ablation studies show a pathway towards maximizing patient outcomes while optimizing the machine-expert collaboration for various scenarios.