Mammograms Classification Using Multiresolution Transforms and Convolution Neural Networks
Goriparthi Prathibha, Bollineni Sai Mohan · 2018
Most of the women in the world are suffering from breast cancer. Many CAD systems have been developed for early detection of breast cancer to increase the life span of the patient for a few years. In this paper work has been done on three class classification of mammograms from Digital Database for Screening Mammography (DDSM) using CNN-Bandelet, CNN-Orthogonal Ripplet Type II(ORT II), CNN-Tetrolet Transform. The coefficients extracted from the region of interest(ROI) of the mammograms are given as input to the Convolution Neural Network(CNN) for the classification of mammograms extracted from Lumisys and Howtek scanners of DDSM database in to normal, benign and malignant. The accuracy using CNN-Bandelet, CNN-ORT II and CNN-Tetrolet is 84.6%, 85.4% and 80.96% respectively.