Detection of Liver Diseases in Computed Tomography Scan Images Using Artificial Neural Networks

Abstract

Liver is one of the most important organ in the human body, it performs a variety of vital functions. Liver cancer is a pathological disorder of the human that affects around 50 million people worldwide. The early detection and diagnosis of liver cancer is very important to facilitate the treatment process. The objective of this study is to design and develop an automated system for liver CT images diagnosis as normal or abnormal to help physicians in their diagnosis and treatment plan. The proposed system performs an automatic segmentation of liver region after applying different enhancement techniques, then the features are extracted from the segmented liver region using Haralick’s feature, this step is followed by features selection and reduction to choose the best representative features. As final step selected features are classified into two classes normal or abnormal. Artificial Neural Network (ANN) and Support Vector Machine (SVM) are applied in the classification step, then the results of them are compared to each other to select the best one and use it to design an automated system.