Tomographic reconstruction with a generative adversarial network.

Xiaogang Yang,Thomas L Sheppard,Andreas Schropp,Johannes Becher,Jan-Dierk Grunwaldt,Dennis Brückner,Yakub Fam,Maik Kahnt,Christian G Schroer

doi:10.1107/s1600577520000831

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.

Highlights

Tomographic imaging is becoming a common tool for many different X-ray imaging techniques at synchrotron light sources, such as transmission X-ray microscopy (TXM), X-ray fluorescence (XRF) imaging and X-ray ptychography (Dierolf et al, 2010; Mino et al, 2018)
We evaluated the performance of the GANrec algorithm with a simulation phantom, extracted from the 3D structure of a shale sample (Fig. 3, top left)
We used this simulation phantom to generate seven groups of tomographic projections with scanning angles of 0–180, 0–170, . . . , 0–120, with one projection per degree. We reconstructed these tomographic projections with the GANrec algorithm and compared the result with those of two other algorithms: the Fourier grid reconstruction algorithm (Gridrec) of Tomopy (Gursoy et al, 2014) and the maximumlikelihood expectation maximization algorithm (MLEM) of Astra (Pelt et al, 2016)

Summary

Introduction

Tomographic imaging is becoming a common tool for many different X-ray imaging techniques at synchrotron light sources, such as transmission X-ray microscopy (TXM), X-ray fluorescence (XRF) imaging and X-ray ptychography (Dierolf et al, 2010; Mino et al, 2018). The development of reconstruction algorithms is still a challenge due to possible imperfections in the measurement data. This is the case for synchrotron radiation applications, as the instrumental setup and data quality vary greatly between different beamlines. X-ray microscopy is often applied in two dimensions to measure functional materials, e.g. catalysts under specific gas and temperature conditions (de Smit et al, 2008; Grunwaldt & Schroer, 2010). Such experiments can provide a great deal of information on sample composi-

Methods

Results

Discussion

Conclusion