Surveys & Reviews

Surveys and reviews in CT reconstruction are papers that organise a body of methods instead of proposing a new one: tutorials, systematic reviews, comparative studies and benchmarks. They are the quickest way into a sub-field, because they fix the notation, name the method families and point at the experiments everyone else compares against.

The reviews collected here span several generations. Older ones explain why filtered back-projection stayed in commercial scanners for decades and how iterative and compressed-sensing reconstruction changed that. Newer ones cover deep learning for tomographic imaging, reconstruction from incomplete projection data and diffusion models for medical imaging, and topic-specific reviews exist for metal artifact reduction, scatter correction and dual-energy CT.

Reviews age quickly in a field that moves this fast. Read one for structure, then check the newest papers on the matching topic page for what has changed since it was written.

Browse all 24 Surveys & Reviews papers in the searchable directory

Start here

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

• Deep Learning for Tomographic Image Reconstruction (Nat Mach Intell, 2020)
  A broad, readable map of deep learning for tomographic reconstruction since 2016 and of the problems it has not solved.
• Solving Inverse Problems Using Data-Driven Models (Acta Numerica, 2019)
  The mathematical foundation for combining learned models with physics-based inverse problems; long, but the standard reference.
• Why do commercial CT scanners still employ traditional, filtered back-projection for image reconstruction? (Inverse Problems, 2009)
  Explains why commercial scanners kept filtered back-projection for decades, which is useful context for any claim that a new method will reach the clinic.
• A Review of Deep Learning CT Reconstruction From Incomplete Projection Data (TRPMS, 2024)
  A recent review that treats sparse-view, limited-angle, metal artifact, interior and ring artifact problems in one framework.
• DM4CT: Benchmarking Diffusion Models for CT Reconstruction (ICLR, 2026 · code)
  A benchmark that compares diffusion models with established CT reconstruction methods under one protocol, with code.

Papers

All 24 papers, newest first.

Browse all 24 Surveys & Reviews papers in the searchable directory

Datasets, benchmarks and toolkits

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

• LoDoPaB-CT (benchmark release paper) · Dataset — The Scientific Data descriptor for the LoDoPaB-CT dataset — the citation to use when you report results on this split. Documents the simulation protocol and the FBP/U-Net reference baseline.
• COBRA2026: a large-scale multicenter pelvic cone-beam computed tomography projection dataset (official page) · Dataset — Projection + image. 867 pelvic radiotherapy CBCT exams from six European centres (Elekta and Varian systems), with raw projections, acquisition geometry, clinical CBCT and planning CT.
• MORE: Multi-Organ Medical Image REconstruction Dataset (official page) · Dataset — CT scans across 9 anatomies and 15 lesion types, built to test generalisation to unseen anatomy rather than a single organ. Released under CC BY-NC 4.0; accepted to ACM MM 2025.
• DeepInverse benchmark suite (official page) · Benchmark — A unified PyTorch benchmark harness covering CT, MRI, deblurring and inpainting, with reproducible metrics and pretrained baselines — the most practical way to compare a new CT method against strong generic solvers.
• DeepInverse · Toolkit — PyTorch library for imaging inverse problems — physics operators, learned denoisers, unrolled networks and benchmarks.

Guides

Guides that cover this topic.

• How to Choose a CT Reconstruction Dataset

Other topics

• Classical & Iterative Reconstruction (71)
• Sparse-View CT (157)
• Limited-Angle Tomography (46)
• Low-Dose CT Denoising (69)
• Metal Artifact Reduction (23)
• Spectral & Dual-Energy CT (19)
• Cone-Beam CT (77)
• Dynamic & 4D CT (24)
• Scatter Correction (11)
• Geometry Calibration & Motion Compensation (28)
• Deep Unrolling & Model-Based Learning (68)
• Self-Supervised & Untrained Methods (35)
• Diffusion & Generative Priors (68)
• Implicit Neural Representations (25)
• Gaussian Splatting (26)