Breast cancer classification using moments

This paper presents a system for detecting breast cancer based on moments. Instead of trying to improve the applied classifier we focused on improving the input attributes. We extracted new features from database samples using the first four moments namely, mean, variance, skewness and kurtosis. Through simulations, 10-fold cross validation method was applied to the Wisconsin breast cancer database to evaluate the classification performances. Various classifiers were used for evaluating the proposed approach. Results indicate advantage of such features in improving classification performance for all of the applied classifiers.