DeepEZ: A Graph Convolutional Network for Automated Epileptogenic Zone Localization From Resting-State fMRI Connectivity

Abstract

Objective: Epileptogenic zone (EZ) localization is a crucial step during diagnostic work up and therapeutic planning in medication refractory epilepsy. In this paper, we present the first deep learning approach to localize the EZ based on resting-state fMRI (rs-fMRI) data. Methods: Our network, called DeepEZ , uses a cascade of graph convolutions that emphasize signal propagation along expected anatomical pathways. We also integrate domain-specific information, such as an asymmetry term on the predicted EZ and a learned subject-specific bias to mitigate environmental confounds. Results: We validate DeepEZ on rs-fMRI collected from 14 patients with focal epilepsy at the University of Wisconsin Madison. Using cross validation, we demonstrate that DeepEZ achieves consistently high EZ localization performance (Accuracy: 0.88 ± 0.03; AUC: 0.73 ± 0.03) that far outstripped any of the baseline methods. This performance is notable given the variability in EZ locations and scanner type across the cohort. Conclusion: Our results highlight the promise of using DeepEZ as an accurate and noninvasive therapeutic planning tool for medication refractory epilepsy. Significance: While prior work in EZ localization focused on identifying localized aberrant signatures, there is growing evidence that epileptic seizures affect inter-regional connectivity in the brain. DeepEZ allows clinicians to harness this information from noninvasive imaging that can easily be integrated into the existing clinical workflow.

The expert's knowledge combined with AI outperforms AI alone in seizure onset zone localization using resting state fMRI

“…The existing methodology, relying on rules outlined by experts and involving detailed manual analysis of numerous ICs, is time-intensive, subjective, and lacks reproducibility. Given the demonstrated capability of large-scale supervised statistical approaches, such as deep learning (DL), to identify abnormal patterns within complex datasets, recent advances have shown their application for SOZ localization from rs-fMRI data ( 18 , 19 ). However, a limited study on 14 subjects with refractory TLE has shown poor positive predictive value (PPV) of 52% (±3.9%) for a brain parcellation to be associated with SOZ ( 19 ).…”

“…Given the demonstrated capability of large-scale supervised statistical approaches, such as deep learning (DL), to identify abnormal patterns within complex datasets, recent advances have shown their application for SOZ localization from rs-fMRI data ( 18 , 19 ). However, a limited study on 14 subjects with refractory TLE has shown poor positive predictive value (PPV) of 52% (±3.9%) for a brain parcellation to be associated with SOZ ( 19 ). Moreover, the identified SOZs do not conform to the disease characteristics, as bilateral SOZ was identified for patients with unilateral focal TLE ( 19 ).…”

“…However, a limited study on 14 subjects with refractory TLE has shown poor positive predictive value (PPV) of 52% (±3.9%) for a brain parcellation to be associated with SOZ ( 19 ). Moreover, the identified SOZs do not conform to the disease characteristics, as bilateral SOZ was identified for patients with unilateral focal TLE ( 19 ). Our prior research has demonstrated that automating the expert rules outlined in ( 16 ) and then implementing them in a carefully structured sequential manner result in a PPV of 65% (±7.8%), surpassing the performance of statistical approaches ( 17 ).…”

“…One of the primary reasons for poor PPV of statistical approaches is that abnormal BOLD correlations, meaning non-noise, not normal resting state fMRI network, and thus is interpreted to be pathological, form <10% of the rs-fMRI ICs from ICA ( 17 , 19 ). This triggers the fundamental Achillies heel of classification science, that is, class imbalance ( 20 ), where the statistical approach lacks enough pathological data to effectively distinguish abnormal patterns amidst significant individual variation.…”

“…Their primary findings suggested the ICA guided by their technique has the potential to identify epilepsy-related ICs in patients with focal epilepsy. Naresh et al ( 19 ) explored deep graph neural networks using the T1-weighted images from rs-fMRI along with diffusion MRI (dMRI) measurements. Study on 14 subjects showed a sensitivity of 40% and precision of 52% while an accuracy of 88%.…”