Magnetic resonance image segmentation and heart motion tracking with an active mesh based system

Abstract

The work presented here relates to a method for motion tracking in sequences of medical images. The purpose is to quantify the general motions and the local deformations of a beating heart during a cardiac cycle. In order to achieve this goal, we first tessellate the first image of the sequence into triangular patches. A Delaunay triangulation is applied to find the optimal set of triangles describing this image, giving a mesh covering the organs. One imposes the contours of the organs to correspond to edges of triangles so that each part of the heart (left ventricle, right ventricle, myocardium) can he described as a different set of triangles, each set indicated by a different color. We then track the nodes of the mesh on the image sequence while imposing them to remain on the edges of the different parts of the heart.