Latent feature mining of spatial and marginal characteristics for mammographic mass classification

Mass classification is one of the key procedures in mammography computer-aided diagnosis (CAD) system, which is widely applied to help improving clinic diagnosis performance. In literature, classical mass classification systems always employ a large number and types of features for discriminating masses. This will produce higher computational complexity. And the incompatibility among various features also may introduce some negative impact to classification accuracy. Furthermore, latent characteristics of masses are seldom considered in the present scheme, which are useful to reveal hidden distribution pattern of masses. For the above purpose, the paper proposes a new mammographic mass classification scheme. Mammograms are detected and segmented first for obtaining region of interests with masses (ROIms). Then Latent Dirichlet Allocation (LDA) is introduced to find hidden topic distribution of ROIms. A special spatial pyramid structure is proposed and incorporated with LDA for capturing latent spatial characteristics of ROIms. For mining latent statistical marginal characteristics of masses, local patches on segmented boundary are extracted to construct a special document for LDA. Finally, all the latent topics will be combined, analyzed and classified by employing the SVM classifier. The experimental results on a dataset in DDSM demonstrate the effectiveness and efficiency of the proposed classification scheme.