Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Automatic iterative segmentation of multiple sclerosis lesions using Student's t mixture models and probabilistic anatomical atlases in FLAIR images

Full text
Author(s):
Freire, Paulo G. L. [1] ; Ferrari, Ricardo J. [1]
Total Authors: 2
Affiliation:
[1] Univ Fed Sao Carlos, Dept Comp, Rod Washington Luis, Km 235, BR-13565905 Sao Carlos, SP - Brazil
Total Affiliations: 1
Document type: Journal article
Source: COMPUTERS IN BIOLOGY AND MEDICINE; v. 73, p. 10-23, JUN 1 2016.
Web of Science Citations: 4
Abstract

Multiple sclerosis (MS) is a demyelinating autoimmune disease that attacks the central nervous system (CNS) and affects more than 2 million people worldwide. The segmentation of MS lesions in magnetic resonance imaging (MRI) is a very important task to assess how a patient is responding to treatment and how the disease is progressing. Computational approaches have been proposed over the years to segment MS lesions and reduce the amount of time spent on manual delineation and inter- and intra-rater variability and bias. However, fully-automatic segmentation of MS lesions still remains an open problem. In this work, we propose an iterative approach using Student's t mixture models and probabilistic anatomical atlases to automatically segment MS lesions in Fluid Attenuated Inversion Recovery (FLAIR) images. Our technique resembles a refinement approach by iteratively segmenting brain tissues into smaller classes until MS lesions are grouped as the most hyperintense one. To validate our technique we used 21 clinical images from the 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge dataset. Evaluation using Dice Similarity Coefficient (DSC), True Positive Ratio (TPR), False Positive Ratio (FPR), Volume Difference (VD) and Pearson's r coefficient shows that our technique has a good spatial and volumetric agreement with raters' manual delineations. Also, a comparison between our proposal and the state-of-the-art shows that our technique is comparable and, in some cases, better than some approaches, thus being a viable alternative for automatic MS lesion segmentation in MRI. (C) 2016 Elsevier Ltd. All rights reserved. (AU)

FAPESP's process: 14/00019-6 - Segmentation of multiple sclerosis lesions in magnetic resonance images using Student's t-distribution mixture model and outliers detection
Grantee:Paulo Guilherme de Lima Freire
Support type: Scholarships in Brazil - Master
FAPESP's process: 12/03100-3 - Research and development of automatic techniques for the detection, segmentation and analysis of multiple sclerosis plaques in magnetic resonance images
Grantee:Ricardo José Ferrari
Support type: Regular Research Grants