Hierarchical 3D Shape Model for Segmentation of 4D MR Cardiac Images

摘要

A novel method for the segmentation of 4D MR cardiac images is introduced in this paper. The method improves the traditional active shape model method by adopting an 3D spatially hierarchical expression of the shape model, which is used as an internal regulation force during the segmentation process. Generation of the landmarks for constructing the shape model is based on the active surface method itself utilizing the long range image force, gradient vector flow (GVF). For constructing hierarchical statistical shape models, initial land-marking is done on a manually segmented training set with different spatial resolutions. Principal component analysis is then used to derive the hierarchical expression of the shape model. Experimental results for 4D MR cardiac image segmentation are presented.