Computational Analysis of Simulated Images Generated in Public Health Centers in Sao Paulo - Brazil

摘要

Currently it is customary to use the CAD scheme to get better results in the early detection of breast cancer. The objective of this work is to evaluate whether such scheme can be useful in the image qualification process associated with the quality control tests. Phantom images generated in some diagnosis centers were analyzed using the CAD through contrast, the quality control test results and entrance skin air kerma values. It was possible to conclude that some attributes of the CAD scheme can contribute for image qualification based on signal-to-noise ratio and pixel intensity variation. These parameters can be useful for a detailed analysis of different density tissues shown in the simulated image.