PMID- 26198360 OWN - NLM STAT- MEDLINE DCOM- 20160929 LR - 20170726 IS - 1879-0771 (Electronic) IS - 0895-6111 (Linking) VI - 46 Pt 1 DP - 2015 Dec TI - Sparse group composition for robust left ventricular epicardium segmentation. PG - 56-63 LID - S0895-6111(15)00096-8 [pii] LID - 10.1016/j.compmedimag.2015.06.003 [doi] AB - Left ventricular (LV) epicardium segmentation in cardiac magnetic resonance images (MRIs) is still a challenging task, where the a-priori knowledge like those that incorporate the heart shape model is usually used to derive reasonable segmentation results. In this paper, we propose a sparse group composition (SGC) approach to model multiple shapes simultaneously, which extends conventional sparsity-based single shape prior modeling to incorporate a-priori spatial constraint information among multiple shapes on-the-fly. Multiple interrelated shapes (shapes of epi- and endo-cardium of myocardium in the case of LV epicardium segmentation) are regarded as a group, and sparse linear composition of training groups is computed to approximate the input group. A framework of iterative procedure of refinement based on SGC and segmentation based on deformation model is utilized for LV epicardium segmentation, in which an improved shape-constraint gradient Chan-Vese model (GCV) acted as deformation model. Compared with the standard sparsity-based single shape prior modeling, the refinement procedure has strong robust for relative gross and not much sparse errors in the input shape and the initial epicardium location can be estimated without complicated landmark detection due to modeling spatial constraint information among multiple shapes effectively. Proposed method was validated on 45 cardiac cine-MR clinical datasets and the results were compared with expert contours. The average perpendicular distance (APD) error of contours is 1.50+/-0.29mm, and the dice metric (DM) is 0.96+/-0.01. Compared to the state-of-the-art methods, our proposed approach appealed competitive segmentation performance and improved robustness. CI - Copyright (c) 2015 Elsevier Ltd. All rights reserved. FAU - Wang, Bing AU - Wang B AD - College of Mathematics and Information Science, Hebei University, Baoding, China. FAU - Gu, Xiaomeng AU - Gu X AD - Multi-disciplinary Research Center, Hebei University, Baoding, China. FAU - Fan, Chonghao AU - Fan C AD - Multi-disciplinary Research Center, Hebei University, Baoding, China. FAU - Xie, Hongzhi AU - Xie H AD - Department of Cardiovascular, Peking Union Medical College Hospital, Beijing, China. Electronic address: xiehongzhi@medmail.com.cn. FAU - Zhang, Shuyang AU - Zhang S AD - Department of Cardiovascular, Peking Union Medical College Hospital, Beijing, China. FAU - Tian, Xuedong AU - Tian X AD - College of Computer Science, Hebei University, Baoding, China. FAU - Gu, Lixu AU - Gu L AD - Multi-disciplinary Research Center, Hebei University, Baoding, China; School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China. Electronic address: gulixu@sjtu.edu.cn. LA - eng PT - Journal Article PT - Research Support, Non-U.S. Gov't DEP - 20150703 PL - United States TA - Comput Med Imaging Graph JT - Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society JID - 8806104 SB - IM MH - *Algorithms MH - Heart Ventricles/*anatomy & histology MH - Humans MH - Image Interpretation, Computer-Assisted/*methods MH - Magnetic Resonance Imaging MH - Models, Cardiovascular MH - Pattern Recognition, Automated/*methods MH - Pericardium/*anatomy & histology MH - Ventricular Function/physiology OTO - NOTNLM OT - Gradient Chan-Vese (GCV) model OT - LV epicardium segmentation OT - Multi-shape prior modeling OT - Sparse group composition EDAT- 2015/07/23 06:00 MHDA- 2016/09/30 06:00 CRDT- 2015/07/23 06:00 PHST- 2015/01/23 00:00 [received] PHST- 2015/06/20 00:00 [revised] PHST- 2015/06/22 00:00 [accepted] PHST- 2015/07/23 06:00 [entrez] PHST- 2015/07/23 06:00 [pubmed] PHST- 2016/09/30 06:00 [medline] AID - S0895-6111(15)00096-8 [pii] AID - 10.1016/j.compmedimag.2015.06.003 [doi] PST - ppublish SO - Comput Med Imaging Graph. 2015 Dec;46 Pt 1:56-63. doi: 10.1016/j.compmedimag.2015.06.003. Epub 2015 Jul 3.