Automated detection of bottom-of-sulcus dysplasia on magnetic resonance imaging-positron emission tomography in patients with drug-resistant focal epilepsy.
Authors
Affiliations (11)
Affiliations (11)
- Department of Neurology, Royal Children's Hospital, Parkville, Victoria, Australia.
- Neuroscience, Murdoch Children's Research Institute, Parkville, Victoria, Australia.
- Department of Paediatrics, University of Melbourne, Melbourne, Victoria, Australia.
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria, Australia.
- Department of Medicine, University of Melbourne, Melbourne, Victoria, Australia.
- Mass General Brigham, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Psychiatry, University of Melbourne, Melbourne, Victoria, Australia.
- Department of Neurosurgery, Royal Children's Hospital, Parkville, Victoria, Australia.
- Developmental Imaging, Murdoch Children's Research Institute, Parkville, Victoria, Australia.
- Department of Medical Imaging, Royal Children's Hospital, Parkville, Victoria, Australia.
- Austin Hospital, Heidelberg, Victoria, Australia.
Abstract
Bottom-of-sulcus dysplasia (BOSD) is a diagnostically challenging subtype of focal cortical dysplasia, 60% being missed on magnetic resonance imaging (MRI). Automated MRI-based detection methods have been developed for focal cortical dysplasia, but not BOSD specifically, and few methods incorporate fluorodeoxyglucose positron emission tomography (FDG-PET) alongside MRI features. We report the development and performance of an automated BOSD detector using combined MRI + PET. The training set comprised 54 patients with focal epilepsy and BOSD. The test sets comprised 17 subsequently diagnosed patients with BOSD from the same center, and 12 published patients from a different center. Across training and test sets, 81% of patients had normal initial MRIs and most BOSDs were <1.5 cm<sup>3</sup>. In the training set, 12 features from T1-MRI, fluid-attenuated inversion recovery-MRI, and FDG-PET were evaluated to determine which features best distinguished dysplastic from normal-appearing cortex. Using the Multi-centre Epilepsy Lesion Detection group's machine-learning detection method with the addition of FDG-PET, neural network classifiers were then trained and tested on MRI + PET, MRI-only, and PET-only features. The proportion of patients whose BOSD was overlapped by the top output cluster, and the top five output clusters, were determined. Cortical and subcortical hypometabolism on FDG-PET was superior in discriminating dysplastic from normal-appearing cortex compared to MRI features. When the BOSD detector was trained on MRI + PET features, 87% BOSDs were overlapped by one of the top five clusters (69% top cluster) in the training set, 94% in the prospective test set (88% top cluster), and 75% in the published test set (58% top cluster). Cluster overlap was generally lower when the detector was trained and tested on PET-only or MRI-only features. Detection of BOSD is possible using established MRI-based automated detection methods, supplemented with FDG-PET features and trained on a BOSD-specific cohort. In clinically appropriate patients with seemingly negative MRI, the detector could suggest MRI regions to scrutinize for possible BOSD.