Unsupervised 4D myocardium segmentation with a Markov Random Field based deformable model

A stochastic deformable model is proposed for the segmentation of the myocardium in Magnetic Resonance Imaging. The segmentation is posed as a probabilistic optimization problem in which the optimal time-dependent surface is obtained for the myocardium of the heart in a discrete space of locations built upon simple geometric assumptions. For this purpose, first, the left ventricle is detected by a set of image analysis tools gathered from the literature. Then, the segmentation solution is obtained by the Maximization of the Posterior Marginals for the myocardium location in a Markov Random Field framework which optimally integrates temporal-spatial smoothness with intensity and gradient related features in an unsupervised way by the Maximum Likelihood estimation of the parameters of the field. This scheme provides a flexible and robust segmentation method which has been able to generate results comparable to manually segmented images for some derived cardiac function parameters in a set of 43 patients affected in different degrees by an Acute Myocardial Infarction.

Main steps of the algorithm. The input of the algorithm is a 4D cardiac image (in blue). The output is the myocardial segmentation (in red). The myocardium is first detected and then segmented by a MRF of deformations.Figure optionsDownload high-quality image (139 K)Download as PowerPoint slideResearch highlights
► Optimal and adaptive combination of intensity, gradient and smoothness features for segmentation.
► 4D approach inside the Markovian deformable model paradigm.
► Coupling of endocardial and epicardial surfaces for myocardial segmentation.
► Hierarchical confinement of the search space for the myocardium.
► Robust, precise and reproducible results in myocardial segmentation.