Neural network based breast cancer classifier using electrical impedance

Breast cancer is one of the leading causes of mortality among women, and the early diagnosis is of significant clinical importance. In this paper, neural network based classifier is proposed which used the electrical impedance data as input data set. Multi-Layer Perceptron (MLP), network is designed with systematic experimentation. In our experiments, we utilize the criteria of mean squared error and absolute classification accuracy to concretely evaluate the performances of the NN based classifier. The experimental results demonstrate that the proposed classifier works as an elegant classifier with the accuracy of 96%.