Echocardiography is a non-invasive method for monitoring ventricular function and evaluating myocardial hypertrophy in patients with heart disease. Although the information displayed in two-dimensional echocardiograms is generally the most useful for diagnostic purposes, one-dimensional or M-Mode echocardiography, due to its greater reliability, is widely accepted as the reference method for the evaluation of myocardial wall thickness. To facilitate quantitative assessment and to minimize potential errors, we have developed two computational approaches allowing the automated extraction of myocardial borders. The first technique uses a set of predefined matched filters to enhance border characteristics. The extraction of cardiac boundaries is achieved by determining optimal paths along the time direction. The second approach uses a radically different strategy. It computes an estimate of an elastic deformation (warping) function allowing the mapping of a measurement obtained at a
