Using Texture of Tissue Surrounding Microcalcifications on Mammograms for Breast Cancer Diagnosis

Computer-aided systems in mammography focus on detection and characterization/diagnosis of lesions (masses and microcalcifications). Characterization of microcalcifications (MCs) is challenged by the presence of dense breast parenchyma, resulting in low specificity values and thus in unnecessary biopsies. Automated characterization of MCs is mainly based on morphology analysis; the current study investigates whether texture properties of the tissue surrounding MCs can contribute to a more accurate breast cancer diagnosis. A case sample of 100 mammographic images, originating from the Digital Database for Screening Mammography (DDSM) database, is analyzed. All mammograms selected have heterogeneously and extremely dense breast patterns and contain subtle MCs (46 benign, 54 malignant, according to database ground truth tables). Regions of interest (ROIs) of 128x128 pixels, containing the MCs are used for the subsequent texture analysis. ROIs are preprocessed using a wavelet-based contrast enhancement method and a thresholding technique is applied to exclude MCs. Texture features are extracted from the remaining ROI area (surrounding tissue) employing co-occurrence matrices, grey level run length matrices and Laws’ texture energy measures. Differentiation between malignant and benign MCs is performed using a k-nearest neighbour (KNN) classifier and employing the leave-one-out training-testing methodology. The KNN classifier achieved an overall accuracy of 89%, sensitivity 90.74% (49 of 54 malignant cases classified correctly) and specificity 86.96% (40 of the 46 benign cases classified correctly). Texture analysis of the tissue surrounding MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of benign (unnecessary) biopsies.