A New Approach for Liver Classification Using Ridgelet / Ripplet-II Transforms, Feature Groups and ANN

Abstract

In this study, 68 liver MR images (28 of them labeled as hemangioma, 40 of them labeled as cyst by specialist radiologists) were classified by using artificial neural network (ANN). Ridgelet transform and its advanced new generation form (called Ripplet-II transform) were applied on these images to compare their effects on liver image classification. Feature vectors were generated by calculating mean, standard deviation, variance, skewness, kurtosis and moment values of coefficient matrices. Firstly, all feature vectors were given as inputs to an ANN and classification process was realized. Then, vectors were seperated into three groups and classified by using three ANNs. This procedure was repeated with two ANNs and two groups of feature vectors. Outputs of the systems which used more than one ANN were evaluated by implementing AND and OR operations seperately. Accuracy, sensitivity and specifity values of obtained results were calculated and compared. The best results were achieved by evaluating the system which used three ANNs and three groups of statistical feature vectors, with AND / OR operations.