Breast tissue removal for enhancing microcalcification cluster detection in mammograms

In this paper, we propose a novel normal breast tissue removal approach using sparse representation (SR), in order to emphasize subtle microcalcifications (MCs) for MC cluster (MCC) detection in mammograms. The proposed method adopts SR to estimate normal breast tissue texture only; such that the difference between estimated image and the original image can emphasize subtle MCs. Comparative experiments have been conducted to validate the effectiveness of the proposed preprocessing with the publicly available DDSM database. The experimental results showed that the MCC detection performances in terms of FROC were improved with the proposed approach compared with the commonly used wavelet decomposition approach. Furthermore, the improved detection performance increases the overall performance for the malignant MCC classification.