摘要
Here we present a method for the simultaneous segmentation of white matter lesions and normal-appearing neuroanatomical structures from multi-contrast brain MRI scans of multiple sclerosis patients. The method integrates a novel model for white matter lesions into a previously validated generative model for whole-brain segmentation. By using separate models for the shape of anatomical structures and their appearance in MRI, the algorithm can adapt to data acquired with different scanners and imaging protocols without retraining. We validate the method using four disparate datasets, showing robust performance in white matter lesion segmentation while simultaneously segmenting dozens of other brain structures. We further demonstrate that the contrast-adaptive method can also be safely applied to MRI scans of healthy controls, and replicate previously documented atrophy patterns in deep gray matter structures in MS. The algorithm is publicly available as part of the open-source neuroimaging package FreeSurfer.
学科与关键词
- A Model of Population and Subject (MOPS) Intensities With Application to Multiple Sclerosis Lesion SegmentationTomas-Fernandez, Xavier*; Warfield, Simon K.IEEE Transactions on Medical Imaging, 2015, 34(6): 1349-1361.被引 47
- A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesionsShiee, Navid*; Bazin, Pierre-Louis; Ozturk, Arzu; Reich, Daniel S.; Calabresi, Peter A.; Pham, Dzung L.NeuroImage, 2010, 49(2): 1524-1535.被引 253
- Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS studyde Sitter, Alexandra*; Steenwijk, Martijn D.; Ruet, Aurelie; Versteeg, Adriaan; Liu, Yaou; van Schijndel, Ronald A.; Pouwels, Petra J. W.; Kilsdonk, Iris D.; Cover, Keith S.; van Dijk, Bob W.; Ropele, Stefan; Rocca, Maria A.; Yiannakas, Marios; Wattjes, Mike P.; Damangir, Soheil; Frisoni, Giovanni B.; Sastre-Garriga, Jaume; Rovira, Alex; Enzinger, Christian; Filippi, Massimo; Frederiksen, Jette; Ciccarelli, Olga; Kappos, Ludwig; Barkhof, Frederik; Vrenken, HugoNeuroImage, 2017, 163: 106-114.被引 25
