Surface Registration in the Presence of Missing Patches and Topology Change

Abstract

The fusion between an endoscopic movie and a CT poses a special surface registration problem. The surface extracted from CT is complete and accurate, whereas the surface extracted from endoscopy suffers from serious missing patches and topology change. We propose a surface registration method, Thin Shell Demons, that is robust under these two situations. Motivated by Thirion’s Demons idea, the partial surface can provide virtual forces to attract the complete surface, which is equipped with a novel physics-based deformation energy. This energy can help preserve the correct surface topology while producing realistic deformation for the regions that don’t have any attracting counterpart regions. The attraction direction assures the deformation is not affected by the surface completeness. Moreover, we propose to use geometric feature matching for computing virtual forces to handle inaccurate 3D point positions and large deformations. We test our method for CT/endoscope fusion and show its potential to achieve successful registration.

Publication
Medical Image Understanding and Analysis - MIUA 2015. 19th Annual Conference, University of Lincoln, Lincoln, UK, July 15-17, 2015
Marc Niethammer
Marc Niethammer
Professor of Computer Science

My research interests include image registration, image segmentation, shape analysis, machine learning, and biomedical applications.

Related