Analysis of Ct Liver Images for Tumour Diagnosis Based on Clustering Technique and Texture Features

The CAD system employs automatic tumor segmentation, texture feature extraction and characterization into Normal malignant and benign tumors. The CT liver image will be classified automatically by probabilistic neural network and texture features. The liver segmentation process will be done by region growing method. The fuzzy c means clustering is used here for effective segmentation to diagnose the tumor part. The morphological process will be used to avoid distortion from background and smoothing the region.