A multi-scale geometric flow for segmenting vasculature in MRI

Often in neurosurgical planning a dual echo acquisition is performed that yields proton density (PD) and T2-weighted images to evaluate edema near a tumour or lesion. The development of vessel segmentation algorithms for PD images is of general interest since this type of acquisition is widespread and is entirely noninvasive. Whereas vessels are signaled by black blood contrast in such images, extracting them is a challenge because other anatomical structures also yield similar contrasts at their boundaries. In this paper we present a novel multi-scale geometric flow for segmenting vasculature from PD images which can also be applied to the easier cases of computed tomography (CT) angiography data or Gadolinium enhanced MRI. The key idea is to first apply Frangi's vesselness measure [4] to find putative centerlines of tubular structures along with their estimated radii. This multi-scale measure is then distributed to create a vector field which is orthogonal to vessel boundaries so that the flux maximizing flow algorithm of [ 17] can be applied to recover them. We validate the approach qualitatively with PD, angiography and Gadolinium enhanced MRI volumes.