A Computer Aided Diagnosis System in Mammography Using Artificial Neural Networks

In this paper we present a method for developing a fully automated computer aided diagnosis (CAD) system to help radiologist in detecting and diagnosing micro-calcifications (MCCs) in digital format mammograms. One aim of the CAD system is to increase the effectiveness and efficiency of screening procedures by using computer. Another aim of the CAD is to extract and analyze the characteristics of vary lesions in an objective manner, then can improve the diagnostic accuracy and reduce the numbers of false-positive diagnoses of malignancies. Automatic segmentation, features extraction, suspicious area detection, classification and a back propagation neural network (BPNN) techniques were used in the development of this system. And the BPNN was used to classifying the marked regions into benign and malignant as the most important stage.