Trimmed-Likelihood Estimation for Focal Lesions and Tissue Segmentation in Multisequence MRI for Multiple Sclerosis

被引：57

作者：

Garcia-Lorenzo, Daniel ^{[1
,2
,3
,4
]}

Prima, Sylvain ^{[1
,2
,3
]}

Arnold, Douglas L. ^{[4
]}

Collins, D. Louis ^{[4
]}

Barillot, Christian ^{[1
,2
,3
]}

机构：

[1] Univ Rennes 1, CNRS, UMR 6074, IRISA, F-35042 Rennes, France

[2] INRIA, VisAGeS Unit Project U746, IRISA, F-35042 Rennes, France

[3] INSERM, VisAGeS Unit Project U746, IRISA, F-35042 Rennes, France

[4] McGill Univ, McConnell Brain Imaging Ctr, Montreal Neurol Inst, Montreal, PQ H3A 2T5, Canada

来源：

IEEE TRANSACTIONS ON MEDICAL IMAGING | 2011年 / 30卷 / 08期

关键词：

Expectation-maximization (EM); Gaussian mixture model; magnetic resonance imaging (MRI); multiple sclerosis; segmentation; FULLY-AUTOMATIC SEGMENTATION; WHITE-MATTER LESIONS; MAXIMUM-LIKELIHOOD; IMAGES; QUANTIFICATION; MIXTURES; COMBINATION; ALGORITHM;

D O I：

10.1109/TMI.2011.2114671

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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).

引用

页码：1455 / 1467

页数：13

共 50 条

[1] Fully automatic segmentation of white matter hyperintensities in MR images of the elderly [J].

Admiraal-Behloul, F ;

van den Heuvel, DMJ ;

Olofsen, H ;

van Osch, MJP ;

van der Grond, J ;

van Buchem, MA ;

Relber, JHC .

NEUROIMAGE, 2005, 28 (03) :607-617

[2]

Aït-Ali LS, 2005, LECT NOTES COMPUT SC, V3749, P409

[3] Automatic Segmentation and Classification of Multiple Sclerosis in Multichannel MRI [J].

Akselrod-Ballin, Ayelet ;

Galun, Meirav ;

Gomori, John Moshe ;

Filippi, Massimo ;

Valsasina, Paola ;

Basri, Ronen ;

Brandt, Achi .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2009, 56 (10) :2461-2469

[4] Probabilistic segmentation of white lesions in MR imaging [J].

Anbeek, P ;

Vincken, KL ;

van Osch, MJP ;

Bisschops, RHC ;

van der Grond, J .

NEUROIMAGE, 2004, 21 (03) :1037-1044

[5]

[Anonymous], 2008 MICCAI WORKSH M

[6] Comparison of MRI criteria at first presentation to predict conversion to clinically definite multiple sclerosis [J].

Barkhof, F ;

Filippi, M ;

Miller, DH ;

Scheltens, P ;

Campi, A ;

Polman, CH ;

Comi, G ;

Ader, HJ ;

Losseff, N ;

Valk, J .

BRAIN, 1997, 120 :2059-2069

[7] Degeneracy in the maximum likelihood estimation of univariate Gaussian mixtures with EM [J].

Biernacki, C ;

Chrétien, S .

STATISTICS & PROBABILITY LETTERS, 2003, 61 (04) :373-382

[8] Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models [J].

Biernacki, C ;

Celeux, G ;

Govaert, G .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2003, 41 (3-4) :561-575

[9] MARKOVIAN SEGMENTATION OF 3D BRAIN MRI TO DETECT MULTIPLE SCLEROSIS LESIONS [J].

Bricq, S. ;

Collet, Ch. ;

Armspach, J. -P. .

2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5, 2008, :733-736

[10] AUTOMATIC 3D INTERSUBJECT REGISTRATION OF MR VOLUMETRIC DATA IN STANDARDIZED TALAIRACH SPACE [J].

COLLINS, DL ;

NEELIN, P ;

PETERS, TM ;

EVANS, AC .

JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1994, 18 (02) :192-205

← 1 2 3 4 5 →