A Computer-Based Decision Support System for Breast Cancer Diagnosis

Abstract

Abstract : The optimal goal of this project is to develop decision support systems for breast cancer diagnosis, treatment option, prognosis, and risk prediction. The primary goal for the first year is to develop visual presentation methods for the consultation system. We have developed an automated and intelligent procedure for generating the hierarchy of minimax entropy models and principal component visualization spaces for improving data explanation. The proposed model is both statistically principled and visually effective at revealing all of the interesting aspects of the data set. The methods involve multiple use of standard finite normal mixture models and probabilistic principal component projections, whose parameters are estimated using expectation-maximization algorithm and principal component neural networks under the information theoretic criteria.