AN EFFICIENT AUTOMATIC MASS CLASSIFICATION METHOD IN DIGITIZED MAMMOGRAMS USING ARTIFICIAL NEURAL NETWORK

In this paper we present an efficient computer aided mass classification method in digitizedmammograms using Artificial Neural Network (ANN), which performs benign-malignant classification onregion of interest (ROI) that contains mass. One of the major mammographic characteristics for massclassification is texture. ANN exploits this important factor to classify the mass into benign or malignant. The statistical textural features used in characterizing the masses are mean, standard deviation, entropy, skewness, kurtosis and uniformity. The main aim of the method is to increase the effectiveness andefficiency of the classification process in an objective manner to reduce the numbers of false-positive ofmalignancies. Three layers artificial neural network (ANN) with seven features was proposed forclassifying the marked regions into benign and malignant and 90.91% sensitivity and 83.87% specificityis achieved that is very much promising compare to the radiologistʹs sensitivity 75%