# Sinogram upsampling using Primal-Dual UNet for undersampled CT and radial MRI reconstruction

arXiv: https://arxiv.org/abs/2112.13443 · HTML: https://mlsanity.com/paper/2112.13443/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 26 Dec 2021.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [Image reconstruction by domain transform manifold learning](https://mlsanity.com/paper/1704.08841/) (2017)
- [Deep learning for undersampled MRI reconstruction](https://mlsanity.com/paper/1709.02576/) (2017)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction](https://mlsanity.com/paper/1803.00694/) (2018)
- [TorchRadon: Fast Differentiable Routines for Computed Tomography](https://mlsanity.com/paper/2009.14788/) (2020)
- [Learning Multiscale Convolutional Dictionaries for Image Reconstruction](https://mlsanity.com/paper/2011.12815/) (2020)
- [ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial Data](https://mlsanity.com/paper/2103.09203/) (2021)

## Built on by (most cited first, 6 of 6)

- [Importance-Aware Adaptive Dataset Distillation](https://mlsanity.com/paper/2401.15863/) (2024)
- [Primal-Dual UNet for Sparse View Cone Beam Computed Tomography Volume Reconstruction](https://mlsanity.com/paper/2205.07866/) (2022)
- [A Deep Learning Approach Using Masked Image Modeling for Reconstruction of Undersampled K-spaces](https://mlsanity.com/paper/2208.11472/) (2022)
- [Data-Driven Interpolation for Super-Scarce X-Ray Computed Tomography](https://mlsanity.com/paper/2205.07888/) (2022)
- [Stereo X-ray Tomography](https://mlsanity.com/paper/2302.13207/) (2023)
- [Evaluating the Safety of Deep Learning-Based Brain MRI Reconstruction](https://mlsanity.com/paper/2608.28714/) (2026)

## Abstract (arXiv)

Computed tomography and magnetic resonance imaging are two widely used clinical imaging modalities for non-invasive diagnosis. However, both of these modalities come with certain problems. CT uses harmful ionising radiation, and MRI suffers from slow acquisition speed. Both problems can be tackled by undersampling, such as sparse sampling. However, such undersampled data leads to lower resolution and introduces artefacts. Several techniques, including deep learning based methods, have been proposed to reconstruct such data. However, the undersampled reconstruction problem for these two modalities was always considered as two different problems and tackled separately by different research works. This paper proposes a unified solution for both sparse CT and undersampled radial MRI reconstruction, achieved by applying Fourier transform-based pre-processing on the radial MRI and then finally reconstructing both modalities using sinogram upsampling combined with filtered back-projection. The Primal-Dual network is a deep learning based method for reconstructing sparsely-sampled CT data. This paper introduces Primal-Dual UNet, which improves the Primal-Dual network in terms of accuracy and reconstruction speed. The proposed method resulted in an average SSIM of 0.932textpm0.021 while performing sparse CT reconstruction for fan-beam geometry with a sparsity level of 16, achieving a statistically significant improvement over the previous model, which resulted in 0.919textpm0.016. Furthermore, the proposed model resulted in 0.903textpm0.019 and 0.957textpm0.023 average SSIM while reconstructing undersampled brain and abdominal MRI data with an acceleration factor of 16, respectively - statistically significant improvements over the original model, which resulted in 0.867textpm0.025 and 0.949textpm0.025.