Devising a deep neural network based mammography phantom image filtering algorithm using images obtained under mAs and kVp control

Figure 1 Mammographic accreditation phantom, phantom image, and diagram. By step-wise adjustment of radiation exposure factors (mAs, kVp), phantom images were obtained within all mAs (60–220) and kVp (22–32) intervals. Figure 4 The whole process and the architecture of the deep neural network based phantom shape scoring models. Phantom image filtering using the modelsPhantom image filtering algorithm (PFA)The filtering algorithms were structured with two steps. Figure 5 The phantom image filtering using the deep neural network based phantom shape scoring (DPS) models.