A CAD System for Detection and Classification of Liver Cirrhosis using Artificial Neural Network and Support Vector Machine

Abstract

In this paper, a computer aided system is designed to determine the extent to which the blood indices, fibro-scan and liver biopsy can help diagnose liver cirrhosis in patients withChronic Hepatitis C.A novel approach, for feature selection is created and used to reduce the extracted features to their best informative subset. The performance of three classifiers is investigated. One is the Support Vector Machine(SVM) with cross-validation, the second is a Multilayer Perception neural network (MLP), and the third isGeneralized RegressionNeural Network(GRNN). The system resulted in anaccuracy of 100% in both training and validation phases for SVM and MLP and 99.50 % for GRNN