Comparison of Fuzzy and Neural Network Models to Diagnose Breast Cancer

Abstract

The automatic diagnosis of breast cancer is an important, real-world medical problem. A major class of problems in Medical Science involves the diagnosis of disease, based upon various tests performed upon the patient. When several tests are involved, the ultimate diagnosis may be difficult to obtain, even for a medical expert. This has given rise, over the past few decades, to computerized diagnostic tools, intended to aid the Physician in making sense out of the confusion of data. This Paper carried out to generate and evaluate both fuzzy and neural network models to predict malignancy of breast tumor, using Wisconsin Diagnosis Breast Cancer Database (WDBC). Our objectives in this Paper are: (i) to compare the diagnostic performance of fuzzy and neural network models in distinction between malignance and benign patterns, (ii) to reduce the number of benign cases sent for biopsy using the best model as a supportive tool, and (iii) to validate the capability of each model to recognize new cases.