DocumentCode :
1515716
Title :
Automated segmentation of multiple sclerosis lesions by model outlier detection
Author :
Van Leemput, Koen ; Maes, Frederik ; Vandermeulen, Dirk ; Colchester, Alan ; Suetens, Paul
Author_Institution :
Fac. of Med. & Eng., Univ. Hosp. Gasthuisberg, Leuven, Belgium
Volume :
20
Issue :
8
fYear :
2001
Firstpage :
677
Lastpage :
688
Abstract :
This paper presents a fully automated algorithm for segmentation of multiple sclerosis (MS) lesions from multispectral magnetic resonance (MR) images. The method performs intensity-based tissue classification using a stochastic model for normal brain images and simultaneously detects MS lesions as outliers that are not well explained by the model. It corrects for MR field inhomogeneities, estimates tissue-specific intensity models from the data itself, and incorporates contextual information in the classification using a Markov random field. The results of the automated method are compared with lesion delineations by human experts, showing a high total lesion load correlation. When the degree of spatial correspondence between segmentations is taken into account, considerable disagreement is found, both between expect segmentations, and between expert and automatic measurements.
Keywords :
biomedical MRI; brain models; diseases; image classification; image segmentation; medical image processing; MR field inhomogeneities correction; Markov random field; automatic measurements; digital brain atlas; expert measurements; fully automated algorithm; intensity-based tissue classification; lesion load correlation; medical diagnostic imaging; multispectral magnetic resonance images; normal brain images; stochastic model; tissue-specific intensity models; Brain modeling; Context modeling; Humans; Image segmentation; Lesions; Magnetic field measurement; Magnetic resonance; Markov random fields; Multiple sclerosis; Stochastic processes; Algorithms; Brain; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Multiple Sclerosis;
fLanguage :
English
Journal_Title :
Medical Imaging, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0062
Type :
jour
DOI :
10.1109/42.938237
Filename :
938237
Link To Document :
بازگشت