Medisys
Medical Imaging Systems Lab at Yonsei University
A Streak Artifact Reduction Algorithm in Sparse-View CT using a
Self-Supervised Neural Representation
A Streak Artifact Reduction Algorithm in Sparse-View CT using a
Self-Supervised Neural Representation
B. Kim, H. Shim, and J. Baek | Medical Physics (Editor's Choice)
Figure 1: Overall framework of the proposed method for streak artifact reduction in sparse-view CT images.
Figure 7: Sparse-view CT reconstruction results of FBP, TV-IR, FBPConvNet, neural representation (denoted as Neur. Repr.), and the proposed method with and without BM3D on the Mayo Clinic data. The red boxes indicate regions of interest. The display window was [−160, 240] in HU.
Figure 9: Enlarged regions of interest images in Figure 7. The display window was [−160, 240] in HU.
Convolutional Neural Network-Based Metal and Streak Artifacts Reduction in
Dental CT Images with Sparse-View Sampling Scheme
Convolutional Neural Network-Based Metal and Streak Artifacts Reduction in
Dental CT Images with Sparse-View Sampling Scheme
S. Kim, J. Ahn, B. Kim, C. Kim, and J. Baek | Medical Physics
Figure 1: Overview of the proposed method for metal and streak artifacts reduction in sparse-view CT image.
Figure 8: The results on clinical datasets from 128 projection views. The ROI images are zoomed in for comparison. The display window is [0 1400] in HU.