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

Source: [Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction](<https://www.sota2.com/research/paper/68fa7f651e209131cea9a14a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:29.249Z

Authors: Alexander Denker, Maximilian Schmidt, Johannes Leuschner, Peter Maass, Jens Behrmann

Published: 2020-06-11T09:23:00.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [CT Image Reconstruction on LoDoPaB-CT challenge](<https://www.sota2.com/research/sota/ct-image-reconstruction-on-lodopab-ct-challenge.md>): CT Image Reconstruction; LoDoPaB-CT challenge; Mean Position: 34.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.06270>)

[PDF](<https://arxiv.org/pdf/2006.06270.pdf>)