Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data

Thomas Germer, Jan Robine, Sebastian Konietzny, Stefan Harmeling, Tobias Uelwer
9/13/2023
eess.IVcs.CV

No official code found. Best implementation: 99991/HTC2022-TUD-HHU-version-1 (4 stars, last commit 2024-03-07).

Abstract

Computed tomography (CT) has become an essential part of modern science and medicine. A CT scanner consists of an X-ray source that is spun around an object of interest. On the opposite end of the X-ray source, a detector captures X-rays that are not absorbed by the object. The reconstruction of an image is a linear inverse problem, which is usually solved by filtered back projection. However, when the number of measurements is small, the reconstruction problem is ill-posed. This is for example the case when the X-ray source is not spun completely around the object, but rather irradiates the object only from a limited angle. To tackle this problem, we present a deep neural network that is trained on a large amount of carefully-crafted synthetic data and can perform limited-angle tomography reconstruction even for only 30° or 40° sinograms. With our approach we won the first place in the Helsinki Tomography Challenge 2022.

View on arXivView PDF

Code Implementations(1)

99991/HTC2022-TUD-HHU-version-1Community100%

An entry for the Helsinki Tomography Challenge 2022 https://www.fips.fi/HTC2022.php

42PythonNov 3, 20222 years agoNOASSERTION

Similar Papers

Stretched sinograms for limited-angle tomographic reconstruction with neural networks

90% match2023

PYRO-NN: Python Reconstruction Operators in Neural Networks

85% match2 repos1222019

Learned Primal-dual Reconstruction

84% match1 repo4342017

DRACO: Differentiable Reconstruction for Arbitrary CBCT Orbits

84% match1 repo92024

Improving the Generalisation of Learned Reconstruction Frameworks

84% match2025

TomoGRAF: A Robust and Generalizable Reconstruction Network for Single-View Computed Tomography

84% match2024

Cite this paper

@article{germer2023limitedangle,
  title  = {Limited-Angle Tomography Reconstruction via Deep End-To-End Learning on Synthetic Data},
  author = {Thomas Germer and Jan Robine and Sebastian Konietzny and Stefan Harmeling and Tobias Uelwer},
  year   = {2023},
  eprint = {2309.06948},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.06948v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.06948.svg)](https://codeofpaper.com/paper/2309.06948)

Discussion