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

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