Fig. 7From: Artifact suppression for breast specimen imaging in micro CBCT using deep learningThe reconstructed images from different methods: (a) the reference image, (b) conventional FBP, (c) IR, (d) FBP with linear-interpolated sinograms, (e) denoised FBP with ResU-Net, (f) the sinograms with U-Net, and (g) the synthesized sinograms with the modified U-Net and ResU-Net models in the proposed methodBack to article page