Automated detection of cortical dysplasia type II in MRI-negative epilepsy

• Published in: Neurology Vol. 83; no. 1; p. 48
• Main Authors: Hong, Seok-Jun, Kim, Hosung, Schrader, Dewi, Bernasconi, Neda, Bernhardt, Boris C, Bernasconi, Andrea
• Format: Journal Article
• Language: English
• Published: United States 01.07.2014
• Subjects: Adult; Automatic Data Processing - methods; Brain - pathology; Brain Mapping; Epilepsy - etiology; Female; Humans; Magnetic Resonance Imaging; Male; Malformations of Cortical Development - complications; Malformations of Cortical Development - diagnosis; Sensitivity and Specificity; Young Adult
• ISSN: 1526-632X
• DOI: 10.1212/wnl.0000000000000543

To detect automatically focal cortical dysplasia (FCD) type II in patients with extratemporal epilepsy initially diagnosed as MRI-negative on routine inspection of 1.5 and 3.0T scans. We implemented an automated classifier relying on surface-based features of FCD morphology and intensity, taking advantage of their covariance. The method was tested on 19 patients (15 with histologically confirmed FCD) scanned at 3.0T, and cross-validated using a leave-one-out strategy. We assessed specificity in 24 healthy controls and 11 disease controls with temporal lobe epilepsy. Cross-dataset classification performance was evaluated in 20 healthy controls and 14 patients with histologically verified FCD examined at 1.5T. Sensitivity was 74%, with 100% specificity (i.e., no lesions detected in healthy or disease controls). In 50% of cases, a single cluster colocalized with the FCD lesion, while in the remaining cases a median of 1 extralesional cluster was found. Applying the classifier (trained on 3.0T data) to the 1.5T dataset yielded comparable performance (sensitivity 71%, specificity 95%). In patients initially diagnosed as MRI-negative, our fully automated multivariate approach offered a substantial gain in sensitivity over standard radiologic assessment. The proposed method showed generalizability across cohorts, scanners, and field strengths. Machine learning may assist presurgical decision-making by facilitating hypothesis formulation about the epileptogenic zone. This study provides Class II evidence that automated machine learning of MRI patterns accurately identifies FCD among patients with extratemporal epilepsy initially diagnosed as MRI-negative.