Semi-automatic segmentation algorithm for pet oncology images

摘要

An apparatus and method for segmenting three-dimensional (3D) medical images containing a region of interest (200) is provided that identifies a first set of seed points within (202) the region of interest (200) and a second set of seed points outside (204) the region of interest (200). A first sphere (210) is constructed within the region of interest (200). Voxels contained within the medical image are classified using a spatial constrained fuzzy clustering algorithm. A plurality of second spheres (220) is generated. Ones of the plurality of second spheres (220) are accepted that satisfy the homogeneity function threshold as defined by the spatial constricted fuzzy clustering algorithm. A three-dimensional area is grown that defines the region of interest (200). The region of interest (200) defined by the three-dimensional area is displayed.