Abstract
Automatic segmentation of liver tumorous regions often fails due to high noise and large variance of tumors. In this work, a semi-automatic algorithm is proposed to segment liver tumors from computed tomography (CT) images. To cope with the variance of tumors, their intensity probability density functions (PDF) are modeled as a bag of Gaussians unlike the previous works where the tumor is modeled as a single Gaussian, and employ a three-dimensional seeded region growing (SRG) method. The bag of Gaussians are initialized at manually selected seeds and updated during growing process iteratively. There are two criteria to be fulfilled for growing: one is the Bayesian decision rule, and the other is a model matching measure. Once the growing is terminated, morphological operations are performed to refine the result. This method, showing promising performance, has been evaluated using ten CT scans of livers with twenty tumors provided by the organizer of the 3D Liver Tumor Segmentation Challenge 2008.
Keywords
Source Code and Data
No source code files available for this publication.
Reviews
Xiang Deng
Friday 25 July 2008
This paper presents a semi-automatic live tumor segmentation technique.
In this method, the tumor is segmented using 3D region growing and Bayesian classification.
Detailed comments:
1) Could the authors provide more detailed information about selection of seed points, i.e., how many seed points should be used for inhomogeneous lesions?
2) Since the selection of seed point is the only user-intervention required, it would be helpful to test the sensitivity/repeatability of the proposed technique against independent initialization.
3) How are the multiple Gaussian distributions combined into one?