| Title: |
Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks: A MELD Study |
| Authors: |
Ripart, Mathilde; Spitzer, Hannah; Williams, Logan ZJ; Walger, Lennart; Chen, Andrew; Napolitano, Antonio; Rossi-Espagnet, Camilla; Foldes, Stephen T; Hu, Wenhan; Mo, Jiajie; Likeman, Marcus; Rüber, Theodor; Caligiuri, Maria Eugenia; Gambardella, Antonio; Guttler, Christopher; Tietze, Anna; Lenge, Matteo; Guerrini, Renzo; Cohen, Nathan T; Wang, Irene; Kloster, Ane; Pinborg, Lars H; Hamandi, Khalid; Jackson, Graeme; Tortora, Domenico; Tisdall, Martin; Conde-Blanco, Estefania; Pariente, Jose C; Perez-Enriquez, Carmen; Gonzalez-Ortiz, Sofia; Mullatti, Nandini; Vecchiato, Katy; Liu, Yawu; Kalviainen, Reetta; Sokol, Drahoslav; Shetty, Jay; Sinclair, Benjamin; Vivash, Lucy; Willard, Anna; Winston, Gavin P; Yasuda, Clarissa; Cendes, Fernando; Shinohara, Russell T; Duncan, John S; Cross, J Helen; Baldeweg, Torsten; Robinson, Emma C; Iglesias, Juan Eugenio; Adler, Sophie; Wagstyl, Konrad; MELD FCD writing group; Fawaz, Abdulah; De Benedictis, Alessandro; De Palma, Luca; Zhang, Kai; Labate, Angelo; Barba, Carmen; You, Xiaozhen; Gaillard, William D; Tang, Yingying; Wang, Shan; Davies, Shirin; Semmelroch, Mira; Severino, Mariasavina; Striano, Pasquale; Chari, Aswin; D'Arco, Felice; Mankad, Kshitij; Bargallo, Nuria; Pascual-Diaz, Saul; Delgado-Martinez, Ignacio; O'Muircheartaigh, Jonathan; Abela, Eugenio; Kandasamy, Jothy; McLellan, Ailsa; Desmond, Patricia; Lui, Elaine; O'Brien, Terence J; Whitaker, Kirstie |
| Source: |
JAMA Neurology (2025) (In press). |
| Publisher Information: |
American Medical Association |
| Publication Year: |
2025 |
| Collection: |
University College London: UCL Discovery |
| Description: |
Importance: A leading cause of surgically remediable, drug-resistant focal epilepsy is focal cortical dysplasia (FCD). FCD is challenging to visualize and often considered magnetic resonance imaging (MRI) negative. Existing automated methods for FCD detection are limited by high numbers of false-positive predictions, hampering their clinical utility. // Objective: To evaluate the efficacy and interpretability of graph neural networks in automatically detecting FCD lesions on MRI scans. // Design, Setting, and Participants: In this multicenter diagnostic study, retrospective MRI data were collated from 23 epilepsy centers worldwide between 2018 and 2022, as part of the Multicenter Epilepsy Lesion Detection (MELD) Project, and analyzed in 2023. Data from 20 centers were split equally into training and testing cohorts, with data from 3 centers withheld for site-independent testing. A graph neural network (MELD Graph) was trained to identify FCD on surface-based features. Network performance was compared with an existing algorithm. Feature analysis, saliencies, and confidence scores were used to interpret network predictions. In total, 34 surface-based MRI features and manual lesion masks were collated from participants, 703 patients with FCD–related epilepsy and 482 controls, and 57 participants were excluded during MRI quality control. // Main Outcomes and Measures: Sensitivity, specificity, and positive predictive value (PPV) of automatically identified lesions. // Results: In the test dataset, the MELD Graph had a sensitivity of 81.6% in histopathologically confirmed patients seizure-free 1 year after surgery and 63.7% in MRI–negative patients with FCD. The PPV of putative lesions from the 260 patients in the test dataset (125 female [48%] and 135 male [52%]; mean age, 18.0 [IQR, 11.0-29.0] years) was 67% (70% sensitivity; 60% specificity), compared with 39% (67% sensitivity; 54% specificity) using an existing baseline algorithm. In the independent test cohort (116 patients; 62 female [53%] and 54 male [47%]; ... |
| Document Type: |
article in journal/newspaper |
| File Description: |
text |
| Language: |
English |
| Relation: |
https://discovery.ucl.ac.uk/id/eprint/10206370/ |
| Availability: |
https://discovery.ucl.ac.uk/id/eprint/10206370/1/Graph-based%20automated%20detection%20of%20Focal%20Cortical%20Dysplasias_%20a%20MELD%20study_open_access.pdf; https://discovery.ucl.ac.uk/id/eprint/10206370/ |
| Rights: |
open |
| Accession Number: |
edsbas.7B7961E2 |
| Database: |
BASE |