BICAD: Breast image computer aided diagnosis for standard BIRADS 1 and 2 in calcifications

The Breast Imaging Reporting and Data System (BIRADS) was developed by the American College of Radiologists as a standard of comparison for rating mammograms and breast ultrasound images. It sets up a classification for the Level of Suspicion (LOS) of the possibility of a breast cancer. In this paper we present an automated image analyzing system that finds calcifications based on the standard BIRADS 1 and 2. For our goal, we studied the digital mammography database in DICOM format provided by the Department of Radiology of the Hospital Universitario de Puebla. We used The Difference of Gaussian (DOG) filter to find edges of the forms of the different calcifications and a back-propagation Artificial Neural Network (ANN) for the pattern recognition of the BIRADS 1 and 2 cases. This method allowed us to automate the segmentation of the calcifications with a low computational cost. We achieved the pattern recognition with a high level of sensitivity of 0.9629 and specificity of 0.9920.