Classification of Masses in Mammography Images Using Wavelet Transform and Neural Networks

In this work, a method for masses and microcalcifications (MCs) classification in the mammography (MG) images was presented. The procedure consists of applying wavelet transform (WT), regions segmentation and multilayer neural network type classifiers. The implemented scheme permits to reduce the iterations number during the training of the neural network MLP applying WT. We adapted Daubechies, Symlet, Coiflet and biorthogonal functions using MLP network for microcalcifications classification in the MG images. The experimental results have shown good performance of the implemented algorithms.