A previous structured images database intended to be used as a tool to researchers testing developed image processing techniques in mammography is being upgraded with new tools and images sets. Its original management system allows to choose and download high quality mammographic images, as from old digitized films as well as from direct digital files acquired more recently. Its search engine is of freely access online, it has incorporated new features, and new types of images intended to aid performance tests of processing schemes. In this sense, we discuss here new tools implemented in the management system to be able to handle images of a new breast phantom with random distributions, exposed to different DR mammography equipment. We described some of the new database management system features to archive, search and download phantom images, together with an evaluation which compares these kind of images with those from actual breasts in order to validate this new set in terms of visual analysis. Previous results not only have indicated a reasonable level of similarity between phantom (ie., simulated) images and actual ones, but the utility of implement this dataset as a section of our mammography database in aiding performance tests of CADx schemes techniques addressed to detect and/or classify signals of interest in digital mammography.

Computer-Aided Diagnosis (CADx) schemes have been proposed to serve as a supplementary image analysis tool in mammography. Experienced radiologists tend to be more assertive to such schemes in assisting their interpretation rather than solely relying on their ability to detect suspicious signals. This study focuses on a simplified version of a previously developed mammography CADx scheme, which was initially designed for digitized film, but is now specifically aimed at classifying breast nodules marked as regions of interest on digital images. This “driven” CADx scheme provides prompt indications regarding whether the selected nodule is deemed normal or suspicious. Its performance was evaluated through tests conducted on different mammograms sets – one with large number of images selected from DDSM database for training, testing and validation of classification parameters, and other comprising direct digital images from InBreast database. Remarkably, similar rates were observed for sensitivity, specificity and accuracy across these two sets (83%, 67% and 72%, respectively). The classification attributes were associated to contour, density and texture. Furthermore, a third test was conducted involving radiologists analyzing digital mammograms obtained from a specific full field digital mammography (FFDM) unit. Results showed that the Driven CADx scheme positively influenced the final diagnoses made by 3 radiologists, consistently increasing accuracy rates. This promising result allows establishing this software as a valuable tool for radiologists in the analysis of masses in digital mammography. The scheme can be implemented on any operating system, or even accessed online.