# Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction

arXiv: https://arxiv.org/abs/2006.06270 · HTML: https://mlsanity.com/paper/2006.06270/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [A Survey on Uncertainty Quantification Methods for Deep Learning](https://mlsanity.com/paper/2302.13425/) (2023)
- [Hallucination Index: An Image Quality Metric for Generative Reconstruction Models](https://mlsanity.com/paper/2407.12780/) (2024)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [Deep Physics-Guided Unrolling Generalization for Compressed Sensing](https://mlsanity.com/paper/2307.08950/) (2023)
- [Synthetic Data in Radiological Imaging: Current State and Future Outlook](https://mlsanity.com/paper/2407.01561/) (2024)
- [Enhanced Low-Dose CT Image Reconstruction by Domain and Task Shifting Gaussian Denoisers](https://mlsanity.com/paper/2403.03551/) (2024)
- [CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing](https://mlsanity.com/paper/2512.09806/) (2025)
- [Unsupervised Low-dose CT Reconstruction with One-way Conditional Normalizing Flows](https://mlsanity.com/paper/2410.17543/) (2024)
- [Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification](https://mlsanity.com/paper/2602.02948/) (2026)

## Abstract (arXiv)

Image reconstruction from computed tomography (CT) measurement is a challenging statistical inverse problem since a high-dimensional conditional distribution needs to be estimated. Based on training data obtained from high-quality reconstructions, we aim to learn a conditional density of images from noisy low-dose CT measurements. To tackle this problem, we propose a hybrid conditional normalizing flow, which integrates the physical model by using the filtered back-projection as conditioner. We evaluate our approach on a low-dose CT benchmark and demonstrate superior performance in terms of structural similarity of our flow-based method compared to other deep learning based approaches.