Yinsheng Li

TL;DR: A two-step processing scheme called 'artifact suppressed large-scale nonlocal means' for suppressing both noise and artifacts in thoracic LDCT images is described, which allows conclusion on the efficacy of the method in improving thoraci LDCT data.

TL;DR: Deep learning method with a common network architecture, termed iCT-Net, was developed and trained to accurately reconstruct images for previously solved and unsolved CT reconstruction problems with high quantitative accuracy, and accurate reconstructions were achieved for the case when the sparse view reconstruction problem is entangled with the classical interior tomographic problems.

TL;DR: A new iterative reconstruction method, synchronized multiartifact reduction with tomographic reconstruction (SMART-RECON), to eliminate limited-view artifacts using data acquired within an ultranarrow temporal window that severely violates the Tuy condition is presented.

TL;DR: A new strategy based on a three-stage process using a large-scale non local means filter (LS-NLM) to suppress the noise and enhance the original CT image, the segmentation of metal artifacts and metallic objects using a mutual information maximized segmentation algorithm (MIMS), and a modified exemplar-based in-painting technique to restore the corrupted projection data in sinogram is proposed.

TL;DR: Qualitative and quantitative performances demonstrate that the proposed sinogram inpainting strategy based on sinusoid-like curve decomposition and eigenvector-guided interpolation can lead to efficient artifact suppression and less structure blurring.