Seok-Jun Hong1, Hosung Kim1, Dewi Schrader1, Neda Bernasconi1, Boris C Bernhardt1, Andrea Bernasconi2. 1. From the NeuroImaging of Epilepsy Laboratory, Department of Neurology and McConnell Brain Imaging Center, McGill University, Montreal Neurological Institute and Hospital, Canada. 2. From the NeuroImaging of Epilepsy Laboratory, Department of Neurology and McConnell Brain Imaging Center, McGill University, Montreal Neurological Institute and Hospital, Canada. andrea@bic.mni.mcgill.ca.
Abstract
OBJECTIVE: 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. METHODS: 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. RESULTS: 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%). CONCLUSION: 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. CLASSIFICATION OF EVIDENCE: 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.
OBJECTIVE: 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. METHODS: 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. RESULTS: 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%). CONCLUSION: 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. CLASSIFICATION OF EVIDENCE: 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.
Authors: N Tzourio-Mazoyer; B Landeau; D Papathanassiou; F Crivello; O Etard; N Delcroix; B Mazoyer; M Joliot Journal: Neuroimage Date: 2002-01 Impact factor: 6.556
Authors: A Bernasconi; S B Antel; D L Collins; N Bernasconi; A Olivier; F Dubeau; G B Pike; F Andermann; D L Arnold Journal: Ann Neurol Date: 2001-06 Impact factor: 10.422
Authors: Yun-Bi Lu; Kristian Franze; Gerald Seifert; Christian Steinhäuser; Frank Kirchhoff; Hartwig Wolburg; Jochen Guck; Paul Janmey; Er-Qing Wei; Josef Käs; Andreas Reichenbach Journal: Proc Natl Acad Sci U S A Date: 2006-11-08 Impact factor: 11.205
Authors: N Usui; K Matsuda; T Mihara; T Tottori; T Ohtsubo; K Baba; N Matsuyama; Y Inoue; K Yagi; Y Kajita; J Yoshida Journal: Neuroradiology Date: 2001-10 Impact factor: 2.804
Authors: A James Barkovich; Renzo Guerrini; Ruben I Kuzniecky; Graeme D Jackson; William B Dobyns Journal: Brain Date: 2012-03-16 Impact factor: 13.501
Authors: Shahin Tavakol; Jessica Royer; Alexander J Lowe; Leonardo Bonilha; Joseph I Tracy; Graeme D Jackson; John S Duncan; Andrea Bernasconi; Neda Bernasconi; Boris C Bernhardt Journal: Epilepsia Date: 2019-03-19 Impact factor: 5.864
Authors: Bilal Ahmed; Carla E Brodley; Karen E Blackmon; Ruben Kuzniecky; Gilad Barash; Chad Carlson; Brian T Quinn; Werner Doyle; Jacqueline French; Orrin Devinsky; Thomas Thesen Journal: Epilepsy Behav Date: 2015-05-31 Impact factor: 2.937