biostudies-literatureSu TYNational Institute of Neurological Disorders and StrokeRosetrees TrustEpilepsy Research Institute UKNINDS NIH HHSWellcome Trust257-271https://www.ebi.ac.uk/biostudies/studies/S-EPMC12893262biostudies-literatureUnknown67(1)<h4>Objective</h4>This study was undertaken to develop a framework for focal cortical dysplasia (FCD) detection using surface-based morphometric (SBM) analysis and machine learning (ML) applied to three-dimensional (3D) magnetic resonance fingerprinting (MRF).<h4>Methods</h4>We included 114 subjects (44 patients with medically intractable focal epilepsy and FCD, 70 healthy controls [HCs]). All subjects underwent high-resolution 3-T MRF scans generating T1 and T2 maps. All patients had clinical T1-weighted (T1w) images; 35 also had 3D fluid-attenuated inversion recovery (FLAIR). A 3D region of interest (ROI) was manually created for each lesion. All maps/images and lesion ROIs were registered to T1w images. Surface-based features were extracted following the Multi-center Epilepsy Lesion DetEpilepsiaSurfaced-based detection of focal cortical dysplasia using magnetic resonance fingerprinting and machine learning.PMC12893262R01 NS1094392R01 NS109439Hu SSu TYBlumcke IAlexopoulos AVWang ZIMurakami HAdler SWagstyl KChoi JYSakaie KJones SEWang XDing ZMa DNajm IfalseSurfaced-based detection of focal cortical dysplasia using magnetic resonance fingerprinting and machine learning.<h4>Objective</h4>This study was undertaken to develop a framework for focal cortical dysplasia (FCD) detection using surface-based morphometric (SBM) analysis and machine learning (ML) applied to three-dimensional (3D) magnetic resonance fingerprinting (MRF).<h4>Methods</h4>We included 114 subjects (44 patients with medically intractable focal epilepsy and FCD, 70 healthy controls [HCs]). All subjects underwent high-resolution 3-T MRF scans generating T1 and T2 maps. All patients had clinical T1-weighted (T1w) images; 35 also had 3D fluid-attenuated inversion recovery (FLAIR). A 3D region of interest (ROI) was manually created for each lesion. All maps/images and lesion ROIs were registered to T1w images. Surface-based features were extracted following the Multi-center Epilepsy Lesion Det2026-01-01T00:00:00Z2026 Jan2026-07-16T09:39:43.591Z2026-07-09T10:46:58.114ZS-EPMC128932624106614910.1111/epi.18667