Left ventricle segmentation in MRI via convex relaxed distribution matching

• Published in: Medical image analysis 2013-12, Vol.17 (8), p.1010-1024
• Main Authors: Nambakhsh, Cyrus M.S., Yuan, Jing, Punithakumar, Kumaradevan, Goela, Aashish, Rajchl, Martin, Peters, Terry M., Ayed, Ismail Ben
• Format: Article
• Language: English
• Subjects: 3D segmentation; Algorithms; Cardiac MRI; Convex-relaxation optimization; Fixed-point optimization; Graphics processing unit; Heart Ventricles - anatomy & histology; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Magnetic Resonance Imaging; Magnetic Resonance Imaging, Cine - methods; Pattern Recognition, Automated - methods; Pericardium - anatomy & histology; Reproducibility of Results; Sensitivity and Specificity
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2013.05.002

[Display omitted] •We investigate fast detection of the left ventricle (LV) endo- and epicardium surfaces in cardiac MRI via convex relaxation and distribution matching.•Our algorithm requires only a single subject for training and a very simple user input, which amounts to a single point per target regions includng cavity or myocardium.•Our parallelized implementation on a graphics processing unit (GPU) demonstrates that the proposed algorithm requires about seconds for a typical cardiac MRI volume, a speed-up of about 5 times in comparison to a standard implementation.•We further demonstrate experimentally that (1) the performance of the algorithm is not significantly affected by the choice of the training subject; and (2) the shape description we use does not change significantly from one subject to another 1. A fundamental step in the diagnosis of cardiovascular diseases, automatic left ventricle (LV) segmentation in cardiac magnetic resonance images (MRIs) is still acknowledged to be a difficult problem. Most of the existing algorithms require either extensive training or intensive user inputs. This study investigates fast detection of the left ventricle (LV) endo- and epicardium surfaces in cardiac MRI via convex relaxation and distribution matching. The algorithm requires a single subject for training and a very simple user input, which amounts to a single point (mouse click) per target region (cavity or myocardium). It seeks cavity and myocardium regions within each 3D phase by optimizing two functionals, each containing two distribution-matching constraints: (1) a distance-based shape prior and (2) an intensity prior. Based on a global measure of similarity between distributions, the shape prior is intrinsically invariant with respect to translation and rotation. We further introduce a scale variable from which we derive a fixed-point equation (FPE), thereby achieving scale-invariance with only few fast computations. The proposed algorithm relaxes the need for costly pose estimation (or registration) procedures and large training sets, and can tolerate shape deformations, unlike template (or atlas) based priors. Our formulation leads to a challenging problem, which is not directly amenable to convex-optimization techniques. For each functional, we split the problem into a sequence of sub-problems, each of which can be solved exactly and globally via a convex relaxation and the augmented Lagrangian method. Unlike related graph-cut approaches, the p