A geometric approach to segmentation and analysis of 3D medical images

Abstract

A geometric scheme for detecting, representing, and measuring 3D medical data is presented. The technique based on deforming 3D surfaces, represented via level-sets, towards the medical objects, according to intrinsic geometric measures of the data. The 3D medical object is represented as a (weighted) minimal surface in a Riemannian space whose metric is induced from the image. This minimal surface is computed using the level-set methodology for propagating interfaces, combined with a narrow band technique which allows fast implementation. This computation technique automatically handles topological changes. Measurements like volume and area are performed on the surface, exploiting the representation and the high accuracy intrinsic to the algorithm.