Automatic 3-D Skeleton-Based Segmentation of Liver Vessels from MRI and CT for Couinaud Representation

Marie-Ange Lèbre, Antoine Vacavant, Manuel Grand-Brochier, Odyssée Merveille, Pascal Chabrot, Armand Abergel, Benoît Magnin

Abstract: Medical imaging systems as MRI and CT, provide useful information on the liver vascular network for surgical planning. However, manual segmentation is difficult and time consuming; an automatic procedure could thus help radiologists in their analysis. CT have been considered superior for hepatic vessels, but they are also visible in MRI, especially when a contrast agent is used. This study proposes an automatic 3-D skeleton-based segmentation for liver vessels. We identify vascular network to propose a segmentation of Couinaud anatomical segments. Experimental results show that the proposed method can segment liver vessels on both modalities with faithful 3-D representations.