A three-dimensional statistical approach to improved image quality for multislice helical CT.

By Jean-Baptiste Thibault, Ken D. Sauer, Charles A. Bouman, Jiang Hsieh. Medical Physics (Lancaster), 2007

1,063 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/79b33b94477515a1c005ac2ce3169c4dec142938

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yi Zhang
2. Satya Prakash Singh
3. Peter B. Noël
4. F. Boas
5. Marcel Beister
6. Chenyu You
7. L. Geyer
8. D. Kolditz

Citations in the corpus

• CT artifacts: Causes and reduction techniques (2012, methodology): “The details in the MBIR image are confirmed in a higher dose FBP image.”
• CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) (2018, methodology): “broadly categorized into the following classes: (1) Modelbased reconstruction methods [13]–[17]: These techniques”
• The evolution of image reconstruction for CT—from filtered back projection to artificial intelligence (2018, background): “These developments fall loosely into three basic approaches: (i) sinogram-based [21 – 23], (ii) image domain-based [24 – 26], and (iii) fully iterative algorithms [18, 27 – 30].”
• Performance comparison between total variation (TV)-based compressed sensing and statistical iterative reconstruction algorithms (2009, methodology): “…can effectively incorporate the knowledge of photon statistics into the image reconstruction process to reduce the noise variance in the final reconstructed images (Sukovic and Clinthorne 2000, De Man et al 2001, Elbakri and Fessler 2002, Li et al 2005, Thibault et al 2007, Wang et al 2008, 2009).”
• 3D Deep Learning on Medical Images: A Review (2020, background): “3D deep networks require a large number of training parameters, especially in the case of 3D medical images, where the depth of the image volume varies from 20 to 400 slices per scan [7,36,79,123], with each scan containing very fine and important information about the patient.”
• A new era of image reconstruction: TrueFidelityTM Technical white paper on deep learning image reconstruction (2019, unknown): “The most comprehensive IR, the so-called model-based iterative reconstruction (MBIR), explicitly accounts for system statistics, X-ray physics, system optics, and patient characteristics all at the same time.(4) To make the solution tractable (i.”
• State of the Art: Iterative CT Reconstruction Techniques. (2015, methodology): “We therefore refer to the publications by Yu et al (25) and Thibault et al (26) for more detailed descriptions.”
• Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation (2015, methodology): “We compare four reconstruction methods–filtered backprojection, MBIR with qGGMRF prior [64], plug-and-play reconstructions with 3D NLM and 3D DSG-NLM as prior models.”
• Iterative reconstruction methods in X-ray CT. (2012, methodology): “All methods can be separated into two groups: source-driven methods, which essentially project each voxel as either a 3D box or a blob (often a sphere) onto the detector image [32,37,38,39] and destination-driven methods, which cast one or multiple rays from the detector pixel position to the x-ray ”
• Low-Dose X-ray CT Reconstruction via Dictionary Learning (2012, unknown): “applied the SIR schemeto real multi-slice helical data [11].”