Segmentation, Reconstruction, Modeling and 3D Visualization of the Ventricles in Echocardiographics Images

This paper addresses the processing and reconstruction of the heart from echocardiographics images. This work is divided into two processing chains: reconstructionvisualization, each one of them is divided in several modules denominated as: 3D Acquisition, 3D Filtration, 3D Segmentation, 3D Reconstruction, 3D Modeling and 3D Visualization. The second processing chain uses a priori model of the organ. It is adjusted to the data issued from the segmentation of the 4D (3D + t) volume captured of the patient. This is a new processing because it is possible to capture a series of useful parameters as (the ejection fraction, position, displacement and torsion of the ventricle) and at the same time it allows to do a 3D visualization of the virtual model. Two different models have been used in this work, a) A model of front propagation that allows to segment the internal wall of the ventricle with enough precision and b) A model with a deformable superquadrics which allows to obtain some useful geometric parameters to describe the shape and the dynamics of the ventricles. When we observe the differences between the virtual model and the result images of the 3D reconstruction of the heart, the physician has more information for the diagnose, then the cardio vascular illnesses will be detected with more precision.