TRACKING GEOMETRICAL DESCRIPTORS ON 3-D DEFORMABLE SURFACES - APPLICATION TO THE LEFT-VENTRICULAR SURFACE OF THE HEART

Motion and deformation analysis of the myocardium are of utmost intere st in cardiac imaging, Part of the research is devoted to the estimati on of the heart function by analysis of the shape changes of the left- ventricular endocardial surface, However, most clinically used shape-b ased approaches are often two-dimensional (2-D) and based on the analy sis of the shape at only two cardiac instants, Three-dimensional (3-D) approaches generally make restrictive hypothesis about the actual end ocardium motion to be able to recover a point-to-point correspondence between two surfaces, The present work is a first step toward the auto matic spatio-temporal analysis and recognition of deformable surfaces, A curvature-based and easily interpretable description of the surface s is derived, Based on this description, shape dynamics is first globa lly estimated through the temporal shape spectra, Second, a regional c urvature-based tracking approach is proposed assuming a smooth deforma tion, It combines geometrical and spatial information in order to anal yze a specific endocardial region, These methods are applied both on t rue 3-D X-ray data and on simulated normal and abnormal left ventricle s, The results are coherent and easily interpretable, Shape dynamics e stimations and comparisons between deformable object sequences are now possible through these techniques, This promising framework is a suit able tool for a complete regional description of deformable surfaces.