Detection of breast cancer using artificial neural networks (ANN)

Abstract

The aim of this project is to design and implement a Matlab based image processing software to extract features of breast cancer images in order to classify disease through neural network in order to examine system accuracy by comparing two techniques of neural networks, feed-forward and back-propagation neural networks. After simulation it was found that the feed forward neural network results are approximately same as the results of back propagation neural network, but from the accuracy side the feed forward neural network (94.11%) is better than the back propagation neural network (92%).