Abstract
Liver cancer is the fifth most commonly diagnosed cancer and the third most common cause of death from cancer worldwide. A precise analysis of the lesions would help in the staging of the tumor and in the evaluation of the possible applicable therapies. In this paper we present the workflow we have developed for the semi-automatic segmentation of liver tumors in the datasets provided for the MICCAI Liver Tumor Segmentation contest. Since we wanted to develop a system that could be as automatic as possible and to follow the segmentation process in every single step starting from the image loading to the lesion extraction, we decided to subdivide the workflow in two main steps: first we focus on the segmentation of the liver and once we have extracted the organ structure we segment the lesions applying an adaptive multi-thresholding system.
Keywords
Source Code and Data
No source code files available for this publication.
Reviews
Xiang Deng
Friday 25 July 2008
The authors presented a semi-automatic live tumor segmentation technique. In this method, the liver is first segmented using watershed algorithm, tumors are then segmented using a minimum cross-entropy multi-thresholding algorithm. The tumor segmentation is further refined with region growing and level-set based surface smoothing methods.
Detailed comments:
1) Overall, this is a nice workshop paper. The presentation is clear.
2) In the multi-thresholding tumor segmentation, the number of thresholds applied in multi-thresholding is 3, with the first and third thresholds set for hypodense and hyperdense tumors respectively. What is the second threshold for?
3) In segmentation refinement, why are the threshold limits not symmetric with respect to the mean value?
4) Could the user manually identified point in the initialization be an arbitrary point in the liver, e.g. a point in normal liver tissue or in the lesion?