Paper Info
Title
Automated Segmentation of MS Lesions from Multi-channel MR Images
Abstract
Quantitative analysis of MR images is becoming increasingly important as a surrogate marker in clinical trials in multiple sclerosis (MS). This paper describes a fully automated model-based method for segmentation of MS lesions from multi-channel MR images. The method simultaneously corrects for MR field inhomogeneities, estimates tissue class distribution parameters and classifies the image voxels. MS lesions are detected as voxels that are not well explained by the model. The results of the automated method are compared with the lesions delineated by human experts, showing a significant total lesion load correlation and an average overall spatial correspondence similar to that between the experts.
Year
DOI
Venue
1999
10.1007/10704282_2
MICCAI
Keywords
Field
DocType
multi-channel mr images,ms lesions,automated segmentation,clinical trial,quantitative analysis
Voxel,Computer vision,Surrogate endpoint,Lesion,Pattern recognition,Computer science,Segmentation,Multiple sclerosis,Multi channel,Artificial intelligence
Conference
Volume
ISSN
ISBN
1679
0302-9743
3-540-66503-X
Citations 
PageRank 
References 
10
7.09
13
Authors
6
Name
Order
Citations
PageRank
Van Leemput Koen11771130.81
Frederik Maes22246273.57
Fernando Bello326142.21
Dirk Vandermeulen42419356.13
Alan C. F. Colchester5634250.27
Paul Suetens62811431.53