Graph Cuts Segmentation with Geometric Shape Priors for Medical Images
Jie Zhu-Jacquot · 2008
In this paper, we propose a novel segmentation method that incorporates geometric shape priors, which do not require statistical training, with the graph cuts technique for robust and efficient segmentations of medical images. We introduce novel terms accounting for shape prior/segmentation and shape prior/image fit to the graph cuts representation. The latter prevents a vicious cycle of inaccurate segmentation/shape priors. We demonstrate the effectiveness of our method on cardiac images and kidney images without strong boundaries.