Shima Sadeghi - Department of Computer Engineering,Arak branch,Islamic Azad University,Arak,Iran
Abbas Karimi - Department of Computer Engineering,Arak branch,Islamic Azad University,Arak,Iran,

Liver cancer is one of the major death factors in the world. Transplantation and tumor removal are two main therapies in common clinical practice. Both tasks need image assisted planning and quantitative evaluations. Both tasks need image assisted planning and quantitative evaluations. Automatic liver segmentation is required forcorresponding quantitative evaluations. Conventional approaches in liver segmentation consist of finding the initial liver border followed by tuning the border to thefinal mask. finding the liver initial border is of great importance as the latter step largely depends on the initial step. Segmentation of CT images to diagnose liver tumors,is faced with constraints. Some of these limitations, Speed, cost and accuracy. In this paper, We Try to use appropriate algorithms to improve the proposed restrictions and new approach segmentation of CT images provide. We use a combination of greedy algorithm and Genetic Algorithm, reduce costs segmentation and Also, achieve high-speed convergence. Results, Demonstrate our superiority over previous methods.

Segmentation, liver tumor, greedy algorithm, genetic algorithm