Paper Info
Title
Trimmed-Likelihood Estimation for Focal Lesions and Tissue Segmentation in Multisequence MRI for Multiple Sclerosis
Abstract
We present a new automatic method for segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. The method performs tissue classification using a model of intensities of the normal appearing brain tissues. In order to estimate the model, a trimmed likelihood estimator is initialized with a hierarchical random approach in order to be robust to MS lesions and other outliers present in real images. The algorithm is first evaluated with simulated images to assess the importance of the robust estimator in presence of outliers. The method is then validated using clinical data in which MS lesions were delineated manually by several experts. Our method obtains an average Dice similarity coefficient (DSC) of 0.65, which is close to the average DSC obtained by raters (0.66).
Year
DOI
Venue
2011
10.1109/TMI.2011.2114671
Medical Imaging, IEEE Transactions
Keywords
Field
DocType
biological tissues,biomedical MRI,brain,cellular biophysics,diseases,image segmentation,medical image processing,neurophysiology,physiological models,average dice similarity coefficient,brain tissues,focal lesions,hierarchical random approach,magnetic resonance imaging,multiple sclerosis lesions,multisequence MRI,robust estimator,tissue segmentation,trimmed-likelihood estimation,Expectation-maximization (EM),Gaussian mixture model,magnetic resonance imaging (MRI),multiple sclerosis,segmentation
Computer vision,Normal distribution,Computer science,Segmentation,Outlier,Robust statistics,Image segmentation,Artificial intelligence,Real image,Mixture model,Estimator
Journal
Volume
Issue
ISSN
30
8
0278-0062
Citations 
PageRank 
References 
13
0.69
21
Authors
6
Name
Order
Citations
PageRank
Daniel García-Lorenzo11598.07
Sylvain Prima274972.13
Douglas L Arnold334031.44
D. Louis Collins43915403.90
Christian Barillot51290133.50
Garcia-Lorenzo, D.6130.69