Awesome Computed Tomography 中文 Star on GitHub

Classical & Iterative Reconstruction

Classical CT reconstruction recovers an image from its line-integral projections with analytical inversion formulas or iterative optimisation, without learned components. Analytical methods, filtered back-projection (FBP) for parallel and fan beams and the Feldkamp-Davis-Kress (FDK) algorithm for cone beams, invert the Radon transform directly and remain the default in most scanners because they are fast and predictable.

Iterative methods treat reconstruction as solving a large linear system or an optimisation problem. Algebraic techniques (ART, SART, SIRT), statistical methods (maximum likelihood, penalised likelihood, model-based iterative reconstruction) and Krylov solvers such as CGLS model the scanner and the noise explicitly, which pays off when data are noisy or incomplete.

Regularisation is what lets iterative methods work with little data: total variation (TV) and its generalisations, wavelet and shearlet sparsity, dictionary learning and non-local penalties. Compressed sensing gave this a theoretical basis around 2006, and these solvers are still the data-consistency backbone inside many deep-learning methods.

Browse all 71 Classical & Iterative Reconstruction papers in the searchable directory

Start here

If you are new to this topic, these are good first reads, chosen by the maintainers.

Papers

The 30 most recent of 71 papers, newest first.

PaperVenueYearLinks
Complex Wavelet-Based Sinogram Segmentation for Metal Artifact Reduction in Cone-Beam CTPMB2026paper
Computed Tomography Reconstruction Algorithm Using Markov Random Field ModelJ. Phys. Soc. Jpn.2026paper
Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CTTMI2026paper
Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image ReconstructionICML2026paper · code · project
Deep Pseudo-Proximal Map: A Self-Supervised Data-Fitting Agent for Iterative Reconstructionpreprint2026paper
H3D-MarNet: Wavelet-Guided Dual-Path Learning for Metal Artifact Suppression and CT Modality Transformation for Radiotherapy WorkflowsICPR2026paper
Model-Based Iterative Reconstruction with View-Dependent Detector Displacements for Cone-Beam CTpreprint2026paper
Radon Transforms of Projection Functions and Aleksandrov-Fenchel Inequalitiespreprint2026paper
Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition SettingsMELBA2026paper · project
Variational Garrote for Sparse Inverse ProblemsJ. Comput. Sci.2026paper
An Iterative Reconstruction Method for Dental Cone-Beam Computed Tomography with a Truncated Field of Viewpreprint2025paper
Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse ProblemsNeurIPS2025paper · code
Learning Wavelet-Sparse FDK for 3D Cone-Beam CT ReconstructionFully3D2025paper
MONSTR: Model-Oriented Neutron Strain Tomographic ReconstructionICIP2025paper
System-Embedded Diffusion Bridge ModelsNeurIPS2025paper · code
Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Seriespreprint2024paper
How auto-differentiation can improve CT workflows: classical algorithms in a modern frameworkOpt. Express2024paper
Iterative reconstruction of low-dose CT based on differential sparseBSPC2023paper
Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative ModelTRPMS2022paper · code
Adversarially learned iterative reconstruction for imaging inverse problemsSSVM2021paper · code
Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS)Med Phys2021paper
FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in ImagingTMI2021paper · code
Limited-Angle CT Reconstruction via the L1/L2 MinimizationSIAM J. Imaging Sci.2021paper
Learning to Reconstruct CT Images From the VVBP-TensorTMI2021paper
FSTensor: Full-spectrum-knowledge-aware tensor model for energy-resolved CT iterative reconstructionTMI2020paper
Radon Inversion via Deep LearningTMI2020paper
Learned convex regularizers for inverse problemspreprint2020paper
Momentum-Net: Fast and convergent iterative neural network for inverse problemsTPAMI2020paper
Moreau-envelope-enhanced nonlocal shearlet transform and total variation for sparse-view CT reconstructionMeas. Sci. Technol.2020paper
Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine LearningProc. IEEE2020paper

Browse all 71 Classical & Iterative Reconstruction papers in the searchable directory

Datasets, benchmarks and toolkits

Entries from the directory whose tasks or tags match this topic.

Guides

Guides that cover this topic.

Other topics