JFET_V6_N2_RP3 Bhagwati Charan Patel G.R. Sinha Journal on Future Engineering and Technology 2230 – 7184 6 2 20 27 Microcalcification, Structural Analysis, Tissue, Receiver Structural Characteristic Identification of Micro-calcifications (MCs) is challenged by the presence of dense breast tissue, resulting in low specificity values and thus in unnecessary biopsies. The current study investigates whether structural properties of the tissue in contiguous MCs can contribute to breast cancer identification. A sample of 75 dense mammographic images affected with malignant and benign were collected from BSR APPOLO for cancer research and diagnosis and included in the digital Database. Regions of Interest (ROIs) containing the MCs were pre-processed using a wavelet based contrast enhancement method, followed by local thresholding to segment MCs; the segmented MCs were excluded from original image ROIs, and the remaining area (in contiguous tissue) was subjected to structural analysis. Four categories of structural features (first order statistics, co-occurrence matrices features, run length matrices features and Laws' structural energy measures) were extracted from the contiguous tissue. The ability of each feature category in discriminating malignant from benign tissue was investigated using a k-closest neighbor (kCN) classifier. Receiver Structural Characteristic (RSC) analysis was conducted for classifier performance evaluation of the individual structural feature categories and of the combined classification scheme. The best performance was achieved by the combined classification scheme yielding an area under the RSC curve of 0.96 (sensitivity 94.4%, specificity 80.0%). Structural analysis of tissue in contiguous MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of unnecessary biopsies. November 2010 - January 2011 Copyright © 2011 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1322