MEDICAL COMPUTER VISION, VIRTUAL-REALITY AND ROBOTICS

The automated analysis of 3D medical images can improve both diagnosis and therapy significantly. This automation raises a number of new fas cinating research problems in the fields of computer vision, graphics and robotics. In this paper, I propose a list of such problems after a review of the current major 3D imaging modalities, and a description of the related medical needs. I then present some of the past and curr ent work done in our research group EPIDAURE at INRIA, on the followi ng topics: segmentation of 3D images; 3D shape modelling; 3D rigid and nonrigid registration; 3D motion analysis; and 3D simulation of thera py. Most topics are discussed in a synthetic manner, and illustrated b y results. Rigid matching is treated more thoroughly as an illustratio n of a transfer from computer vision towards 3D image processing. The later topics are illustrated by preliminary results, and a number of p romising research tracks are suggested.