Tubular objects network detection from 3D images

Abstract

We present an approach to the tree representation of a tubular object network. The full 3D tracking algorithm for a single tubular structure is detailed. Detection of bifurcations by a connectivity approach is then exposed. We show subvoxel accuracy and reliable orientation estimation for the tracking process on synthetic images. Bifurcations are also well detected on a complex synthetic image. Finally, applications of this method to real 3D medical images are shown. The method is particularly suited for processing magnetic resonance angiography of the brain and neck.