Extracting 3D Structures from Biomedical Data

We present a 3D deformable model that is based on a geometrically induced external force field which can be conveniently generalized to arbitrary dimensions. This external force field is based on hypothesized interactions between the relative geometries of the deformable model and the object boundary characterized by image gradient. The evolution of the deformable model is solved using the level set method so as to facilitate topological changes. The proposed external force field can attract the deformable model to object boundaries with arbitrary initialization, and allows the deformable model to reach highly concave regions which are generally difficult for other methods. We provide a comparative study on the segmentation of various geometries in real 3D images, and show that the proposed method achieves significant improvements against existing image gradient techniques.