Application of Evolutionary Programming and Probabilistic Neural Networks to Estimating the Development of Breast Cancer

摘要

Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer benign/malignant classification. That is, will a patient, with specific values of the discriminate indicators, develop breast cancer in the future? The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. In on-going work, these new techniques will be optimized further and should produce results better than or equal to the classical networks, but with more information content and confidence.