Automated segmentation of multiple sclerosis lesions by model outlier detection

Citation
K. Van Leemput et al., Automated segmentation of multiple sclerosis lesions by model outlier detection, IEEE MED IM, 20(8), 2001, pp. 677-688
Citations number
40
Categorie Soggetti
Radiology ,Nuclear Medicine & Imaging","Eletrical & Eletronics Engineeing
Journal title
IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN journal
02780062 → ACNP
Volume
20
Issue
8
Year of publication
2001
Pages
677 - 688
Database
ISI
SICI code
0278-0062(200108)20:8<677:ASOMSL>2.0.ZU;2-Q
Abstract
This paper presents a fully automated algorithm for segmentation of multipl e sclerosis (MS) lesions from multispectral magnetic resonance (MR) images. The method performs intensity-based tissue classification using a stochast ic model for normal brain images and simultaneously detects MS lesions as o utliers that are not well explained by the model. It corrects for MR field inhomogeneities, estimates tissue-specific intensity models from the data i tself, and incorporates contextual information in the classification using a Markov random field. The results of the automated method are compared wit h lesion delineations by human experts, showing a high total lesion load co rrelation. When the degree of spatial correspondence between segmentations is taken into account, considerable disagreement is found, both between exp ert segmentations, and between expert and automatic measurements.