Fast segmentation and modeling of hepatic components for the planning of robot-assisted liver tumor ablation.

Abstract

Segmentation and modeling of hepatic components from pre-operative images is very important for treatment planning and guidance in robot-assisted liver tumor ablation. An in-house developed system for hepatic component segmentation and modeling using CT data is presented in this paper. This system includes gross liver segmentation by a 3D mesh deformation model, liver vasculature segmentation by a vessel context-based voting and grouping method, liver tumor segmentation by a support vector machine framework, and other segmentation/modeling tool. This system was tested using 20 data sets from human patients and 5 sets of porcine CT scan. It is suggested by experimental results that the developed system is able to conduct fast segmentation and modeling of hepatic components for both human and large animal, with a satisfying accuracy, to support treatment planning.