Longitudinal multiple sclerosis lesion segmentation data resource

• Published in: Data in brief Vol. 12; no. C; pp. 346 - 350
• Main Authors: Carass, Aaron, Roy, Snehashis, Jog, Amod, Cuzzocreo, Jennifer L., Magrath, Elizabeth, Gherman, Adrian, Button, Julia, Nguyen, James, Bazin, Pierre-Louis, Calabresi, Peter A., Crainiceanu, Ciprian M., Ellingsen, Lotta M., Reich, Daniel S., Prince, Jerry L., Pham, Dzung L.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.06.2017; Elsevier
• Subjects: automation; Data; humans; Internet; Magnetic resonance imaging; Multiple sclerosis; sclerosis; Magnetic resonance imaging; Multiple sclerosis
• ISSN: 2352-3409; 2352-3409
• DOI: 10.1016/j.dib.2017.04.004

The data presented in this article is related to the research article entitled “Longitudinal multiple sclerosis lesion segmentation: Resource and challenge” (Carass et al., 2017) [1]. In conjunction with the 2015 International Symposium on Biomedical Imaging, we organized a longitudinal multiple sclerosis (MS) lesion segmentation challenge providing training and test data to registered participants. The training data consists of five subjects with a mean of 4.4 (±0.55) time-points, and test data of fourteen subjects with a mean of 4.4 (±0.67) time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. The training data including multi-modal scans and manually delineated lesion masks is available for download.11The data and evaluation website is: http://smart-stats-tools.org/lesion-challenge-2015. In addition, the testing data is also being made available in conjunction with a website for evaluating the automated analysis of the testing data.