000199583 001__ 199583
000199583 005__ 20180913062530.0
000199583 0247_ $$2doi$$a10.1016/j.cmpb.2014.03.003
000199583 022__ $$a0169-2607
000199583 02470 $$2ISI$$a000335392900004
000199583 037__ $$aARTICLE
000199583 245__ $$aMBIS: Multivariate Bayesian Image Segmentation tool
000199583 260__ $$aClare$$bElsevier Ireland Ltd$$c2014
000199583 269__ $$a2014
000199583 300__ $$a19
000199583 336__ $$aJournal Articles
000199583 520__ $$aWe present MBIS (Multivariate Bayesian Image Segmentation tool), a clustering tool based on the mixture of multivariate normal distributions model. MBIS supports multichannel bias field correction based on a B-spline model. A second methodological novelty is the inclusion of graph-cuts optimization for the stationary anisotropic hidden Markov random field model. Along with MBIS, we release an evaluation framework that contains three different experiments on multi-site data. We first validate the accuracy of segmentation and the estimated bias field for each channel. MBIS outperforms a widely used segmentation tool in a cross-comparison evaluation. The second experiment demonstrates the robustness of results on atlas-free segmentation of two image sets from scan-rescan protocols on 21 healthy subjects. Multivariate segmentation is more replicable than the monospectral counterpart on T1-weighted images. Finally, we provide a third experiment to illustrate how MBIS can be used in a large-scale study of tissue volume change with increasing age in 584 healthy subjects. This last result is meaningful as multivariate segmentation performs robustly without the need for prior knowledge. (C) 2014 Elsevier Ireland Ltd. All rights reserved.
000199583 6531_ $$aMultivariate
000199583 6531_ $$aReproducible research
000199583 6531_ $$aImage segmentation
000199583 6531_ $$aGraph-cuts
000199583 6531_ $$aITK
000199583 6531_ $$aLTS5
000199583 6531_ $$aCIBM-SPC
000199583 700__ $$aEsteban, Oscar$$uUniv Politecn Madrid, ETSI Telecomunicac, E-28040 Madrid, Spain
000199583 700__ $$aWollny, Gert$$uUniv Politecn Madrid, ETSI Telecomunicac, E-28040 Madrid, Spain
000199583 700__ $$0242936$$aGorthi, Subrahmanyam$$g182243$$uEcole Polytech Fed Lausanne, Signal Proc Lab LTS5, CH-1015 Lausanne, Switzerland
000199583 700__ $$aLedesma-Carbayo, Maria-J.$$uUniv Politecn Madrid, ETSI Telecomunicac, E-28040 Madrid, Spain
000199583 700__ $$0240323$$aThiran, Jean-Philippe$$g115534$$uEcole Polytech Fed Lausanne, Signal Proc Lab LTS5, CH-1015 Lausanne, Switzerland
000199583 700__ $$aSantos, Andres$$uUniv Politecn Madrid, ETSI Telecomunicac, E-28040 Madrid, Spain
000199583 700__ $$0240463$$aBach-Cuadra, Meritxell$$g124931$$uEcole Polytech Fed Lausanne, Signal Proc Lab LTS5, CH-1015 Lausanne, Switzerland
000199583 773__ $$j115$$k2$$q76-94$$tComputer Methods And Programs In Biomedicine
000199583 909C0 $$0252394$$pLTS5$$xU10954
000199583 909CO $$ooai:infoscience.tind.io:199583$$pSTI$$particle
000199583 917Z8 $$x124931
000199583 917Z8 $$x115534
000199583 937__ $$aEPFL-ARTICLE-199583
000199583 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000199583 980__ $$aARTICLE