Shape constraints for the left ventricle segmentation from cardiac cine MRI based on snake models

Segmentation of the left ventricle (LV) is a hot topic in cardiac magnetic resonance (MR) images analysis. To make thorough use of the anatomical and functional information, it is necessary to segment the endocardium and epicardium of the left ventricle. However, automatic and accurate segmentation of the left ventricle remains a challenging problem because of papillary muscles, lack of edge information, image inhomogeneity and low contrast at the epicardium. In this chapter, we address the shape constraints for extracting the endocardium and epicardium from cardiac cine MRI based on snake models. For endocardium segmentation, a circle/ellipse-based shape energy term is incorporated into the snake model. With this prior constraint, the snake contour can conquer the unexpected local minimum stemming from artifacts and papillary muscle. After extracting the endocardium, the edge map is modified to yield a new external force field for active contours, which automatically pushes the snake contour directly to the epicardium by employing the endocardium result as initialization. However, the circle constraint does not work very well for the epicardium, and the ellipse constraint needs the troublesome calculation of the ellipse orientation during snake evolution. Assuming that the epicardium resembles the endocardium in shape, we further propose a novel shape similarity energy for epicardium segmentation. With this energy, the snake model can avoid being trapped into artifacts and leaking out at weak boundaries. Based on the circle constraint and shape similarity energy, we present an automatic algorithm to extract the endocardium and epicardium of the LV simultaneously. Both qualitative and quantitative evaluations on our dataset and the publicly available database (e.g., MICCAI 2009) demonstrate the good performance of our algorithm.