ABSTRACT
The image segmentation is a core component for medical application. We have studied the feasibility of applying some segmentation techniques for the determination of cardiac efficiency parameters, on echocardiographic image sequence of the left ventricle. To face this first issue in order to structure not invasive medical technique of analysis and to build up an automatic protocol for image sequence analysis. Standard snake models of closed curve evolution, pertaining to the Level-Set Method, have been implemented to characterize the internal ventricular area over time. We have applied standard finite difference techniques for the approximation solution of the involved eikonal equations for front evolution. Wellknown techniques of Gaussian regularization, such as heat equation, have highlighted the loss of definition of ventricular edge Fig. 1a.
