Assessment of global cardiac function in MSCT imaging using fuzzy connectedness segmentation

The goal of this work is to assess global cardiac function in terms of ventricular volume from multi-slice computed tomography dynamic dataset. We propose an approach for the segmentation of the left ventricle and the measurement of the ventricular volume along the whole cardiac cycle. It is based on the segmentation of the left cavities using a fuzzy connectedness algorithm. The interactive placement of a 3D valvular plane is then used to cut through the segmented surface in order to extract the left ventricle. This method provides, with few interactions, the cardiac volume along the whole cardiac cycle and global parameters such as end-cardiac phases volumes and ejection fraction. Results have been compared to measures estimated during clinical routine with MSCT and MRI and have provided satisfying results. The specificity and the sensibility of the method have also been measured by a comparison with a manual segmentation of reference, leading to a very good specificity of the proposed approach.