الفهرس 
abstractOnly 14 pages are availabe for public view
 |  | from | 121 |  |  |
| | | from | 121 | | |
Abstract
In modern medicine, dependency on automated approaches for analysis and diagnosis has been increasing over the years. One of the problems in depending on the human in diagnosis is the experience of the examiner. Liver tumor is one of the highest causes of death due to cancer. Liver cancer, Hepatocellular carcinoma (HCC), is the sixth most common malignant tumor in the world and remains a leading cause of death by cancer worldwide. Automatic identification of CT liver tumor image is a challenging task. In this study, a computer aided diagnosis (CAD) system for identifying the liver tumor as benign or malignant by analyzing CT images is presented. The proposed approach consists of four successive stages. Firstly, image enhancement stage, to improve the quality of the input image. In the second stage, the liver is segmented based on thresholding and boundary extraction algorithms then it is given as input to an adopted Fuzzy C-mean (FCM) clustering algorithm to extract its inside tumor object. The third stage is feature extraction, two feature extraction techniques i.e. Discrete Wavelet Transformation (DWT) and spatial domain technique (texture features) are used to extract the main features of the tumor object to help in the next stage. Finally, tumor identification stage, the Adaptive Neuro Fuzzy Inference System (ANFIS) classifier is trained by these previously extracted sets of features separately to evaluate their performances on the tumor classification in a comparison manner to take a right decision. The proposed method is tested and evaluated on a group of patients’ CT data and experiment show promising results. The classifier achieves 90 % accuracy using GLCM while the accuracy obtained using DWT is 96%.