Abstract
We propose a novel framework for reconstructing 3Dliver vessel model from CT images. The proposed algorithm consists of vessel detection, vessel tree reconstruction and vessel radius estimation. First, we employ the tubular-filter based approach to detect vessel structure and construct the minimum spanning tree to bridge all the gaps between vessels. Then, we propose an approach to estimate the radius of the vessel at all vessel centerline voxels based on the local patch descriptors. Using the proposed 3D vessel reconstruction system can provide detailed 3D liver vessel model very efficiently. Our experimental results demonstrate the accuracy of the proposed system for 3D liver vessel reconstruction from 3D CT images.