Liver and tumor segmentation and analysis from CT of diseased patients

Wednesday, October 26, 2011 — Poster Session III
10:00 a.m. – Noon	Natcher Conference Center	CC	IMAG-21

Authors

• MG Linguraru
• WJ Richbourg
• JM Watt
• V Pamulapati
• RM Summers

Abstract

The poster presents the automated segmentation of livers from abdominal CT images of diseased populations from images with inconsistent enhancement. A novel three-dimensional (3D) affine invariant shape parameterization is employed to compare local shape across organs. By generating a regular sampling of the organ’s surface, this parameterization can be effectively used to compare features of a set of closed 3D surfaces point-to-point while avoiding common problems with the parameterization of concave surfaces. From an initial segmentation, the areas of atypical local shape are determined using training sets. A geodesic active contour corrects locally the segmentations of organs in abnormal images and optimized graph cuts segment the vasculature and hepatic tumors using shape and enhancement constraints. Liver segmentation errors are reduced significantly and the tumor burden is estimated with an error of 1%. Results from test data demonstrate the method's robustness to analyze livers from difficult clinical cases to allow temporal monitoring of patients with hepatic cancer.

back to top