A simple and efficient method for image segmentation with deformable templates

A method for the automated segmentation of images containing structures of interest is presented in this work. The method employs a template image for which a segmentation is available. Segmentation of the target image is achieved by deforming the template so as to maximize a similarity measure of the target and template images. The deformations are chosen in accordance with a viscous fluid model. A simplification of the fluid model proposed elsewhere is shown to retain desirable properties of the deformation while allowing extremely efficient numerical implementation. The technique is validated on both binary and anatomical images.