Application of preoperative MRI lesion identification algorithm in pediatric and young adult focal cortical dysplasia-related epilepsy

• Published in: Seizure (London, England) Vol. 122; pp. 64 - 70
• Main Authors: Hom, Kara L., Illapani, Venkata Sita Priyanka, Xie, Hua, Oluigbo, Chima, Vezina, L. Gilbert, Gaillard, William D., Gholipour, Taha, Cohen, Nathan T.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.11.2024
• Subjects: Adolescent; Adult; Algorithms; Automated detection; Automated MRI segmentation; Brain - diagnostic imaging; Brain - pathology; Child; Child, Preschool; Drug Resistant Epilepsy - diagnostic imaging; Drug Resistant Epilepsy - surgery; Epilepsy - diagnostic imaging; Epilepsy - surgery; Female; Focal Cortical Dysplasia; Humans; Machine learning; Magnetic Resonance Imaging - standards; Male; Malformations of Cortical Development - complications; Malformations of Cortical Development - diagnostic imaging; Malformations of Cortical Development - surgery; Non-lesional focal epilepsy; Retrospective Studies; Sensitivity and Specificity; Structural MRI; Young Adult; Structural MRI; Automated detection; Non-lesional focal epilepsy; Automated MRI segmentation; Focal cortical dysplasia; Machine learning
• ISSN: 1059-1311; 1532-2688; 1532-2688
• DOI: 10.1016/j.seizure.2024.09.024

•MELD algorithm has variable performance across novel pediatric/young adult datasets.•MELD algorithm has high sensitivity for FCDIIB.•MELD algorithm has high sensitivity for FCD Type II in neonatal/infantile patients.•MELD algorithm has clinical utility in simulated real world MRI-negative population. 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. 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. 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. 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.