Multiview myocardial segmentation in echocardiographic images using a piecewise parametric shape prior

The segmentation of the myocardium in echocardiographic images is an important task for the diagnosis of heart diseases. This step is made difficult due to the inherent problems of echographic images (e.g. low contrast, speckle noise). In this article, we propose a method to segment the whole myocardium (endocardium and epicardium) from 2D echographic scans. This is achieved using a level-set model constrained by a new shape formulation that allows to model both contours. The novelty of this work also lays in the fact that our framework allows to segment the myocardium in any view. The method is evaluated on a set of clinical images. The obtained results are compared to expert segmentations and to the results provided by the recent approach described.