Sedigheh Ahmadi - 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, from Support vector machines with minimal user intervention to be used toprecise segmentation. The genetic algorithm was used to features extraction of the CT images of liver tumors. Combining support vector machine and genetic algorithm,accuracy and speed obtained of diagnosis and segmentation is tumor. The results of the proposed method, Showed an improvement in our way.

Segmentation, liver tumor, svm, genetic algorithm,