Extracting branching tubular object geometry via cores.

Abstract

Blood vessels and other anatomic objects in the human body can be described as trees of branching tubes. The focus of this paper is the extraction of the branching geometry in three-dimensional, as well as the extraction of the tubes themselves, via skeletons computed as cores. Cores are height ridges of a graded measure of medial strength called medialness, which measures how much a given location resembles the middle of an object as indicated by image intensities. Object bifurcations are detected using an affine-invariant corner detector and computations on the core's medialness values. The methods presented in this paper are evaluated on synthetic images of branching tubular objects as well as on blood vessels in head MR angiogram data. Results show impressive resistance to noise and the ability to detect branches spanning a variety of widths and branching angles. An extension that allows cores to extract general branching structures, not only branching tubes, is introduced.