# Deep Unfolding of the DBFB Algorithm with Application to ROI CT Imaging with Limited Angular Density

arXiv: https://arxiv.org/abs/2209.13264 · HTML: https://mlsanity.com/paper/2209.13264/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 27 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [Solving ill-posed inverse problems using iterative deep neural networks](https://mlsanity.com/paper/1704.04058/) (2017)
- [TorchRadon: Fast Differentiable Routines for Computed Tomography](https://mlsanity.com/paper/2009.14788/) (2020)
- [Deep Unfolding of a Proximal Interior Point Method for Image Restoration](https://mlsanity.com/paper/1812.04276/) (2018)
- [Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis](https://mlsanity.com/paper/1611.06391/) (2016)
- [Model Learning: Primal Dual Networks for Fast MR imaging](https://mlsanity.com/paper/1908.02426/) (2019)
- [On the Quality of the Initial Basin in Overspecified Neural Networks](https://mlsanity.com/paper/1511.04210/) (2015)
- [Do CNNs solve the CT inverse problem?](https://mlsanity.com/paper/2005.10755/) (2020)
- [Back-Projection based Fidelity Term for Ill-Posed Linear Inverse Problems](https://mlsanity.com/paper/1906.06794/) (2019)
- [Learnable Histogram: Statistical Context Features for Deep Neural Networks](https://mlsanity.com/paper/1804.09398/) (2018)
- [On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objective](https://mlsanity.com/paper/2005.00959/) (2020)
- [The Randomized Kaczmarz Method with Mismatched Adjoint](https://mlsanity.com/paper/1803.02848/) (2018)

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

- [Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance](https://mlsanity.com/paper/2312.16519/) (2023)
- [Unfolded proximal neural networks for robust image Gaussian denoising](https://mlsanity.com/paper/2308.03139/) (2023)
- [Restarted contractive operators to learn at equilibrium](https://mlsanity.com/paper/2506.13239/) (2025)
- [Self-supervised conformal prediction for uncertainty quantification in Poisson imaging problems](https://mlsanity.com/paper/2502.19194/) (2025)
- [Unrolled Graph Neural Networks for Constrained Optimization](https://mlsanity.com/paper/2509.17156/) (2025)
- [RT-SRTS: Angle-Agnostic Real-Time Simultaneous 3D Reconstruction and Tumor Segmentation from Single X-Ray Projection](https://mlsanity.com/paper/2310.08080/) (2023)

## Abstract (arXiv)

This paper presents a new method for reconstructing regions of interest (ROI) from a limited number of computed tomography (CT) measurements. Classical model-based iterative reconstruction methods lead to images with predictable features. Still, they often suffer from tedious parameterization and slow convergence. On the contrary, deep learning methods are fast, and they can reach high reconstruction quality by leveraging information from large datasets, but they lack interpretability. At the crossroads of both methods, deep unfolding networks have been recently proposed. Their design includes the physics of the imaging system and the steps of an iterative optimization algorithm. Motivated by the success of these networks for various applications, we introduce an unfolding neural network called U-RDBFB designed for ROI CT reconstruction from limited data. Few-view truncated data are effectively handled thanks to a robust non-convex data fidelity term combined with a sparsity-inducing regularization function. We unfold the Dual Block coordinate Forward-Backward (DBFB) algorithm, embedded in an iterative reweighted scheme, allowing the learning of key parameters in a supervised manner. Our experiments show an improvement over several state-of-the-art methods, including a model-based iterative scheme, a multi-scale deep learning architecture, and other deep unfolding methods.