Automatic classification and retrieval of mammographic tissue density using texture features

The advancement of medical image digitization and storage is growing day by day and it has resulted in increasing demands for efficient medical image retrieval system. CBIR refers to the retrieval of similar images based on the given query image. Today, Computer Aided Detection/Diagnosis (CAD) schemes that uses CBIR has been attracting research interest. The mammography is the key imagery for early breast cancer diagnosis. The aim of this study is to create a CBIR system based on the type of breast tissue density. First, interleaved candidate blocks are selected from the input mammograms. Then, Haralick texture descriptors were extracted from the candidate blocks of the breast parenchyma. The mean of extracted features are fed into the SVM classifier for classification of the tissue density into any of the three classes namely dense, glandular and fatty and the classification accuracy obtained is 91.51%. For content based retrieval of the mammograms based on the given query image, first the query image is classified into any of the three tissue class. Then the feature vector of the query image is compared with the feature database. Top five similar images are retrieved from its corresponding class database. Euclidean distance based k-NN is used for mammogram retrieval. The results reveal that the proposed method could be employed for effective content based mammogram retrieval.