Segmentation and Classification of Tumour in Computed Tomography Liver Images for Detection, Analysis and Preoperative Planning

Segmentation of CT liver images helps to analyze the presence of hepatic tumor and classify the tumor from images of diseased populations. Here, we use region growing technique to examine the neighboring pixels of initial seed points and determine whether the pixel neighbors should be added to the region or not. The process is iterative and seed point is chosen interactively in the suspected region. The contour generated by the region growing has been segmented using watershed method. The texture features for segmented region are extracted through Grey Level Co-occurrence Matrix (GLCM). These features are used to classify the tumor as benign or malignant using Support Vector Machine (SVM) approach. In this paper, a semi-Automated system has been presented which is robust, allows radiologist and surgeons to have easy and convenient access to organ measurements and visualization. Experimental results shows that liver segmentation errors are reduced significantly and all tumors are segmented from liver and are classified as benign or malignant.