Title
Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS study.
Abstract
•Much-needed study on quantitative evaluation and objective comparison of WM lesion segmentation methods.•Using different scanners and different MR protocols in a real-life setting similar to phase-III trials and everyday clinical practice.•The methods perform almost equally well whether parameter tuning is performed using data from the same center or not.
Year
DOI
Venue
2017
10.1016/j.neuroimage.2017.09.011
NeuroImage
Keywords
Field
DocType
Multiple sclerosis,White matter lesion,Automated methods segmentation,MRI
Lesion,Cognitive psychology,Artificial intelligence,Medicine,Formal testing,Anatomical segmentation,Intraclass correlation,Training set,Mean difference,Computer vision,Pattern recognition,Segmentation,Lesion segmentation
Journal
Volume
ISSN
Citations 
163
1053-8119
1
PageRank 
References 
Authors
0.39
9
25