Skip to main content
. Author manuscript; available in PMC: 2024 Jan 1.
Published in final edited form as: Med Phys. 2022 Sep 28;50(1):89–103. doi: 10.1002/mp.15958

FIGURE 1.

FIGURE 1.

Diagram of DuDoSS. Xsparse reconstructed using sparsely-sampled projections Ssparse was input to the ImgNet to predict the full-view SPECT image Xfull−pred. Then, Xfull−pred was forward-projected to generate a prior full-view projections Sprior, which were then combined with the ground-truth acquired Angle 1 to obtain Sprior−combine. Next, Sprior−combine was input to the SinoNet to generate the predicted sinogram Spred. Finally, Spred was combined with the ground-truth acquired Angle 1 to output the combined projections Spred−combine.