MODEL-BASED BOUNDARY ESTIMATION OF COMPLEX OBJECTS USING HIERARCHICALACTIVE SURFACE TEMPLATES

A method for the segmentation of complex, three-dimensional objects us ing hierarchical active surface templates is presented. The templates consist of one or more active surface models which are specified accor ding to a priori knowledge about the expected shape and location of th e desired object. This allows complex objects to be naturally modeled as collections of simple subparts which are geometrically constrained. The template is adaptively deformed by the three-dimensional image da ta in which it is initialized such that the template boundaries are br ought into correspondence with the assumed image object. An external e nergy field is developed based on a vector distance transform such tha t the surfaces are deformed according to object shape. The method is d emonstrated by the segmentation of the human brain from three-dimensio nal magnetic resonance images of the head given an a priori model of a normal brain.