Whole Heart Region Segmentation from CT and MRI Images Using a Hybrid Model

Image segmentation is a very important pre-requisite in medical image analysis, therapy planning and CAD (Computer Aided Diagnose). Heart segmentation is a difficult task for its similarity in gray level with neighboring organs coursed by tissue conglutination and the complexity of anatomical configuration. Some earlier methods focused on the segmentation of parts of heart, e.g. ventricles, which is much easier even though they are time consuming and do not converge in some cases. In this paper, we present a fast and robust hybrid method for the segmentation of the whole heart, including ventricles and myocardium from CT and MRl images. This method consists of two major steps: The first step focuses on the segmentation of different configurations of heart based on classification method; the second step focuses on getting the boundary of the whole heart and separates it from neighboring organs. At the end of this paper, some experiments have been made to verify the efficiency and the validity of our method.