Published Paper Details:

According to World Health Organization (WHO), breast cancer is most common cancer in woman in worldwide, becoming to one of the most fatal form of cancer. The mammography analysis is an effective technology for early detection of breast cancer. MC (Micro-calcification clusters) is a major part of breast cancer so detection of MC plays an important role in computer aided system (CAD) so to improve the MC detection rate in mammograms. The proposed method comprises the three main steps. Firstly, remove label and pectoral muscle which adopting the largest connected region marking and region growing method, and enhance MCs using the combination of double top-hat transform and grayscale adjustment function, secondly, remove noise and other interference information, and retain the significant information by modifying the contour-let coefficients using nonlinear function and lastly we use the non-linking simplified pulse-coupled neural network to detect MCs. : In our work, we choose 118 mammograms including 38 mammograms with micro-calcification clusters and 80 mammograms without micro-calcification to demonstrate our algorithm separately from two open and common database including the MIAS and JSMIT; and we achieve the higher specificity of 94.7%, sensitivity of 96.3%, AUC of 97.0%, accuracy of 95.8%, MCC of 90.4%, MCC-PS of 61.3% and CEI of 53.5%, these promising results clearly demonstrate that the proposed approach outperforms the current state-of-the-art algorithms.