Tomographic reconstruction with a generative adversarial network

Research output: Contribution to journalArticle

Abstract

This paper presents a deep learning algorithm for tomographic reconstruction (GANrec). The algorithm uses a generative adversarial network (GAN) to solve the inverse of the Radon transform directly. It works for independent sinograms without additional training steps. The GAN has been developed to fit the input sinogram with the model sinogram generated from the predicted reconstruction. Good quality reconstructions can be obtained during the minimization of the fitting errors. The reconstruction is a self-Training procedure based on the physics model, instead of on training data. The algorithm showed significant improvements in the reconstruction accuracy, especially for missing-wedge tomography acquired at less than 180° rotational range. It was also validated by reconstructing a missing-wedge X-ray ptychographic tomography (PXCT) data set of a macroporous zeolite particle, for which only 51 projections over 70° could be collected. The GANrec recovered the 3D pore structure with reasonable quality for further analysis. This reconstruction concept can work universally for most of the ill-posed inverse problems if the forward model is well defined, such as phase retrieval of in-line phase-contrast imaging.

Details

Authors
  • Xiaogang Yang
  • Maik Kahnt
  • Dennis Bruckner
  • Andreas Schropp
  • Yakub Fam
  • Johannes Becher
  • Jan Dierk Grunwaldt
  • Thomas L. Sheppard
  • Christian G. Schroer
Organisations
External organisations
  • German Electron Synchrotron (DESY)
  • University of Hamburg
  • Ruhr-University Bochum
  • Karlsruhe Institute of Technology
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • Atom and Molecular Physics and Optics

Keywords

  • generative adversarial network (GAN), missing-wedge tomography, ptychography, reconstruction algorithms
Original languageEnglish
Pages (from-to)486-493
Number of pages8
JournalJournal of Synchrotron Radiation
Volume27
Publication statusPublished - 2020 Mar 1
Publication categoryResearch
Peer-reviewedYes