Coronary vein tracking from MSCT using a minimum cost path approach
Abstract
In this paper, we deal with the problem of tracking the coronary venous tree from Multi-Slice Computed Tomography (MSCT) angiography. Contrast inhomogeneities are a major issue. The proposed tracking procedure is based on minimum-cost path computation and makes use of `Fast-Marching' technique. The algorithm aims at propagating a front inside a vascular structure and extracting a centered path. To achieve this goal, a specific cost function which combines the vessel local orientation to a vesselness measure is designed. Experiments on synthetic data and real data have been performed. Coronary veins with contrast difficulties are extracted with a low computing time.
Fichier principal
CORONARY_VEIN_TRACKING_FROM_MSCT_USING_A_MINIMUM_COST_PATH_APPROACH.pdf (419.25 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Loading...