Application of evolutionary computation and neural network hybrids for breast cancer classification using mammogram and history data

Mammography is the modality of choice for the early detection of breast cancer, primarily because of its sensitivity to the detection of breast cancer. However, because of its high rate of false positive predictions, a large number of biopsies of benign lesions result. The paper explores the use and evaluates the performance of two neural network hybrids as an aid to radiologists in avoiding biopsies of these benign lesions. These hybrids provide the potential to improve both the sensitivity and specificity of breast cancer diagnosis. The first hybrid, the Generalized Regression Neural Network (GRNN) Oracle, focuses on improving the performance output of a set of learning algorithms that operate and are accurate over the entire (defined) learning space. The second hybrid, an evolutionary programming (EP)/adaptive boosting (AB) based hybrid, intelligently combines the outputs from an iteratively called "weak" learning algorithm (one which performs at least slightly better than random guessing), in order to "boost" the performance of the weak learner. The second part of the paper discusses modifications to improve the EP/AB hybrid's performance, and further evaluates how the use of the EP/AB hybrid may obviate biopsies of benign lesions (as compared to an EP only classification system), given the requirement of missing few if any cancers.