Tom Haeck1, 2, Thijs Dhollander1, 2, Frederik Maes1, 2, Stefan Sunaert1, 3, Paul Suetens1, 2
1Medical Imaging Research Center (MIRC), KU Leuven, Leuven, Belgium; 2Center for Processing Speech and Images (PSI), Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium; 3Department of Radiology, University Hospitals of the KU Leuven, Leuven, Belgium
MR-images of the brain can be segmented by registration with an atlas. A common way to do so is to register the brain volume with an intensity atlas and consequently to propagate the labels of the atlas to the brain volume according to the resulting deformation field. However, most intensity-based registration algorithms fail in the presence of pathologies. This causes gross segmentation errors in the vicinity of the pathology. We study the possibility to improve the robustness of the demons algorithm by minor, easy-to-implement, modifications of the demons force.