Left ventricular analysis from cardiac images using deformable models

An image understanding system that applies flexible constraints in the form of a probabilistic deformable model to the problem of segmenting the left ventricle from cardiac image sequences is discussed. The parametric model is based on the elliptic Fourier decomposition of the boundary. The segmentation problem is solved as an optimization problem, where the best match between the boundary, as defined by the parameter or vector, and the image data is found. From the boundary determined, the motion and shape of the left ventricle can then be characterized to give a quantitative evaluation of cardiac function. The system is a model for the intelligent segmentation of natural objects whose diversity and irregularity of shape makes them poorly represented in terms of fixed features or form. This technique is being applied to radionuclide angiocardiography and two-dimensional echocardiography