A neural network method for mammogram analysis based on statistical features

In this paper, we present a novel approach to the problem of computer-aided analysis of digital mammograms for breast cancer detection. The algorithm developed here classifies mammograms into normal and abnormal. First, the structures in mammograms produced by normal glandular tissue of varying density are eliminated using a wavelet transform (WT) based local average subtraction. Then the linear markings formed by the normal connective tissue are identified and removed. Any abnormality that may exist in the mammogram is therefore enhanced in the residual image, which makes the decision regarding the normality of the mammogram much easier. Statistical descriptors based on high-order statistics derived from the residual image are applied to a probabilistic neural network (PNN) for classification. Using the mammographic data from the Mammographic Image Analysis Society (MIAS) database a recognition score of '71% was achieved.