Intelligent Breast Cancer Diagnosis Using Hybrid GA-ANN

Breast cancer prevails as one of the infamous deathly diseases among women worldwide. Early detection and treatment of breast cancer can increase the survival rate of patients. Presently, the method of diagnosis depends on the human experiences. The method is time-consuming, subjected to human error and cause unnecessary burden to radiologists. This paper introduces an automatic breast cancer diagnosis technique using a genetic algorithm (GA) for simultaneous feature selection and parameter optimization of artificial neural networks (ANN). The performances of the proposed algorithm employing three different variations of the backpropagation technique for the fine tuning of the weight of ANN are compared. The algorithm is called the GAANN_XX where the XX refers to the back-propagation training variation used. The proposed algorithms called GAANN_RP produces the best and average, 99.43% and 98.29% correct classification respectively on the Wiscinson Breast Cancer Dataset.