mlsanityData to 7 Oct 2026

Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

arXiv 2206.07050 ↗First posted 14 Jun 2022eess.IV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect accuracy? Positive evidence is provided for the first time, focusing on a prototypical computed tomography (CT) setup. We demonstrate that an iterative end-to-end network scheme enables reconstructions close to numerical precision, comparable to classical compressed sensing strategies. Our results build on our winning submission to the recent AAPM DL-Sparse-View CT Challenge. Its goal was to identify the state-of-the-art in solving the sparse-view CT inverse problem with data-driven techniques. A specific difficulty of the challenge setup was that the precise forward model remained unknown to the participants. Therefore, a key feature of our approach was to initially estimate the unknown fanbeam geometry in a data-driven calibration step. Apart from an in-depth analysis of our methodology, we also demonstrate its state-of-the-art performance on the open-access real-world dataset LoDoPaB CT.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

31 of 48 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018Group Normalizationcited by 1,514
  4. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  5. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  6. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  7. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  8. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  9. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  10. 2017Learned Primal-dual Reconstructioncited by 251
  11. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  12. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
19 more
  1. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  2. 2020Model-Based Deep Learningcited by 136
  3. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 126
  4. 2016The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentationcited by 122
  5. 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
  6. 2020Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challengecited by 59
  7. 2020Solving Inverse Problems With Deep Neural Networks -- Robustness Included?cited by 58
  8. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  9. 2019Momentum-Net: Fast and convergent iterative neural network for inverse problemscited by 38
  10. 2017Recurrent Inference Machines for Solving Inverse Problemscited by 33
  11. 2018Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomographycited by 29
  12. 2020Model Adaptation for Inverse Problems in Imagingcited by 20
  13. 2021Feasibility-based Fixed Point Networkscited by 17
  14. 2020Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstructioncited by 14
  15. 2020Do CNNs solve the CT inverse problem?cited by 13
  16. 2019Low-Dose CT with Deep Learning Regularization via Proximal Forward Backward Splittingcited by 9
  17. 2020On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objectivecited by 6
  18. 2019dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performancecited by 5
  19. 2020On the unreasonable effectiveness of CNNscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 5; 2025: 1; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  2. 2023Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidancecited by 43
  3. 2023Multilevel CNNs for Parametric PDEscited by 9
  4. 2022Gradient-Based Geometry Learning for Fan-Beam CT Reconstructioncited by 8
  5. 2024Slicer Networkscited by 6
  6. 2023Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Datacited by 5
  7. 2023Improving Automated Hemorrhage Detection in Sparse-view Computed Tomography via Deep Convolutional Neural Network based Artifact Reductioncited by 2
  8. 2024Non-Asymptotic Uncertainty Quantification in High-Dimensional Learningcited by 2
  9. 2024Enhanced Low-Dose CT Image Reconstruction by Domain and Task Shifting Gaussian Denoiserscited by 1
  10. 2024Self-Supervised Denoiser Frameworkcited by 1
  11. 2022Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Imagescited by 0
  12. 2025Improving the Generalisation of Learned Reconstruction Frameworkscited by 0
1 more
  1. 2026Diffusion Based Unpaired Data Learning for Inverse Problemscited by 0