Kernel Adatron implementation for breast cancer data

Breast cancer is a scourge for women, second only to lung cancers as the leading cause of death in women. As an extension of current efforts to improve lesion classification to reduce the number of women having benign lesions referred for biopsy, the Kernel Adatron algorithm has been implemented for the purpose of classifying datasets of mammographic results. The Duke University dataset with 500 cases of non-palpable mammographically suspicious breast lesions in its initial 16 field form and its reduced 7 field form, was used. Testing also include the University of South Florida dataset of 1979 cases.