Analytical software for visual and quantitative comparison of real mammography and phantom breast cancer imaging

Computer-aided diagnostic schemes have been developed with the primary aim of improving the diagnostic accuracy of the detection of cancer in mammography. A robust mammographic image database is a priority requirement to assist in testing the effectiveness of techniques associated with these schemes. However, such datasets—with information on radiological and biopsy reports, different types of findings and good quality images—are difficult to find, mainly due to privacy concerns of different radiology centers and hospitals, and are often limited to the research team involved. Aiming to overcome these issues, we are developing an alternative based on images of a structured breast phantom previously developed in our group. Although having been validated in terms of their physical characteristics, investigating the images produced from this phantom exposure on a digital mammography system is an important task. Therefore, this work’s primary objective is to conduct a comparative analysis between digital images derived from this phantom and real-breast images to assess the degree of visual perception confusion between these two image types. This investigation will help determine the viability of using images from these phantom exposures in creating a database for evaluating the performance of techniques used in CAD schemes in digital mammography. For this purpose, a software was developed for managing comparative tests between images of actual breasts and images from this phantom, considering internal regions of interest. The results were promising, showing a variation of 55–65% in the rate of correct answers among observers, indicating a reasonable level of confusion between the two types of images.