The Expert Knowledge combined with AI outperforms AI Alone in Seizure Onset Zone Localization using resting state fMRI

TL;DR

This study tackles non-invasive localization of seizure onset zones (SOZ) in pediatric refractory epilepsy using resting-state fMRI (rs-fMRI). It introduces an expert knowledge integration (EKI) module that complements deep learning (DL) with rule-based SOZ features, balancing data via SMOTE and exploiting DBSCAN-based localization. The unified approach (SLLEK) significantly outperforms DL alone, achieving an accuracy of $84.8\%$ and F1 of $91.7\%$, with the most discriminative cues being activations that originate in gray matter, traverse white matter, and end in vascular regions. The method aligns well with ic-EEG and post-surgical Engel outcomes, offering explainable, clinically actionable SOZ localization that could streamline pre-surgical planning in pediatric epilepsy and motivate multi-center validation.

Abstract

We evaluated whether integration of expert guidance on seizure onset zone (SOZ) identification from resting state functional MRI (rs-fMRI) connectomics combined with deep learning (DL) techniques enhances the SOZ delineation in patients with refractory epilepsy (RE), compared to utilizing DL alone. Rs-fMRI were collected from 52 children with RE who had subsequently undergone ic-EEG and then, if indicated, surgery for seizure control (n = 25). The resting state functional connectomics data were previously independently classified by two expert epileptologists, as indicative of measurement noise, typical resting state network connectivity, or SOZ. An expert knowledge integrated deep network was trained on functional connectomics data to identify SOZ. Expert knowledge integrated with DL showed a SOZ localization accuracy of 84.8& and F1 score, harmonic mean of positive predictive value and sensitivity, of 91.7%. Conversely, a DL only model yielded an accuracy of less than 50% (F1 score 63%). Activations that initiate in gray matter, extend through white matter and end in vascular regions are seen as the most discriminative expert identified SOZ characteristics. Integration of expert knowledge of functional connectomics can not only enhance the performance of DL in localizing SOZ in RE, but also lead toward potentially useful explanations of prevalent co-activation patterns in SOZ. RE with surgical outcomes and pre-operative rs-fMRI studies can yield expert knowledge most salient for SOZ identification.

Figures (3)

• Figure 1: Overview of the proposed SOZ IC localization. Top panel: preprocessing the data by reducing the image dimensions to alleviate computational overhead. Second panel - top: training involves relabeling RSN and SOZ as non-Noise components. Second panel – bottom: These components are then subjected to CNN. Additionally, we establish an expert knowledge integration model (EKI), which is trained based on the extracted expert knowledge from RSN and SOZ components. Third panel: testing involves classification task of rs-fMRI ICs into three categories: NOISE, RSN and SOZ using both DL and expert knowledge. Bottom panel: localization of SOZ involves identification of biggest cluster amongst a patient’s SOZ slices. The operator $\circ$ denotes dot product.
• Figure 2: Three types of information are encoded in rs-fMRI: NOISE, RSN and SOZ. Each of these categories adheres to specific rules that define their classification.
• Figure 3: Expert Feature extraction and integration process.