Objective: The purpose of this study was to evaluate the performance and generalizability of an automated, interpretable surface-based MRI classifier for the detection of focal cortical dysplasia.
Methods: This was a retrospective cohort incorporating MRIs from the epilepsy surgery (FCD and MRI-negative) and neuroimaging (healthy controls) databases at Children's National Hospital (CNH), and a publicly-available FCD Type II dataset from Bonn, Germany. Clinical characteristics and outcomes were abstracted from patient records and/or existing databases. Subjects were included if they had 3T epilepsy-protocol MRI. Manually-segmented FCD masks were compared to the automated masks generated by the Multi-centre Epilepsy Lesion Detection (MELD) FCD detection algorithm. Sensitivity/specificity were calculated.
Results: From CNH, 39 FCD pharmacoresistant epilepsy (PRE) patients, 19 healthy controls, and 19 MRI-negative patients were included. From Bonn, 85 FCD Type II were included, of which 68 passed preprocessing. MELD had varying performance (sensitivity) in these datasets: CNH FCD-PRE (54 %); Bonn (68 %); MRI-negative (44 %). In multivariate regression, FCD Type IIB pathology predicted higher chance of MELD automated lesion detection. All four patients who underwent resection/ablation of MELD-identified clusters achieved Engel I outcome.
Significance: We validate the performance of MELD automated, interpretable FCD classifier in a diverse pediatric cohort with FCD-PRE. We also demonstrate the classifier has relatively good performance in an independent FCD Type II cohort with pediatric-onset epilepsy, as well as simulated real-world value in a pediatric population with MRI-negative PRE.
Keywords: Automated MRI segmentation; Automated detection; Focal cortical dysplasia; Machine learning; Non-lesional focal epilepsy; Structural MRI.
Copyright © 2024. Published by Elsevier Ltd.