Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Physics-informed 4D x-ray image reconstruction from ultra-sparse spatiotemporal data

Yao, Zisheng LU orcid ; Zhang, Yuhe LU ; Hu, Zhe LU ; Klöfkorn, Robert LU orcid ; Ritschel, Tobias and Villanueva-Perez, Pablo LU orcid (2025) In Measurement Science and Technology 36(8).
Abstract

The unprecedented x-ray flux density provided by modern x-ray sources offers new spatiotemporal possibilities for x-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either (i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or (ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. Four-dimensional (4D) reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for x-ray imaging combine the power of artificial... (More)

The unprecedented x-ray flux density provided by modern x-ray sources offers new spatiotemporal possibilities for x-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either (i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or (ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. Four-dimensional (4D) reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for x-ray imaging combine the power of artificial intelligence and the physics of x-ray propagation to tackle the challenge of sparse views. However, most approaches do not constrain the physics of the studied process, i.e. a full physical model. Here we present 4D physics-informed optimized neural implicit x-ray imaging, a novel physics-informed 4D x-ray image reconstruction method combining the full physical model and a state-of-the-art DL-based reconstruction method for 4D x-ray imaging from sparse views. We demonstrate and evaluate the potential of our approach by retrieving 4D information from ultra-sparse spatiotemporal acquisitions of simulated binary droplet collisions, a relevant fluid dynamic process. We envision that this work will open new spatiotemporal possibilities for various 4D x-ray imaging modalities, such as time-resolved x-ray tomography and more novel sparse acquisition approaches like x-ray multi-projection imaging, which will pave the way for investigations of various rapid 4D dynamics, such as fluid dynamics and composite testing.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
deep learning, four-dimensional (4D) reconstruction, physics-informed, ultra-sparse spatiotemporal data, ultrafast x-ray imaging
in
Measurement Science and Technology
volume
36
issue
8
article number
085403
publisher
IOP Publishing
external identifiers
  • scopus:105012983667
ISSN
0957-0233
DOI
10.1088/1361-6501/adf2c9
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2025 The Author(s). Published by IOP Publishing Ltd.
id
4b8b7688-c205-4af4-b964-3144a24fd6ba
date added to LUP
2025-11-24 13:37:18
date last changed
2025-11-24 13:38:02
@article{4b8b7688-c205-4af4-b964-3144a24fd6ba,
  abstract     = {{<p>The unprecedented x-ray flux density provided by modern x-ray sources offers new spatiotemporal possibilities for x-ray imaging of fast dynamic processes. Approaches to exploit such possibilities often result in either (i) a limited number of projections or spatial information due to limited scanning speed, as in time-resolved tomography, or (ii) a limited number of time points, as in stroboscopic imaging, making the reconstruction problem ill-posed and unlikely to be solved by classical reconstruction approaches. Four-dimensional (4D) reconstruction from such data requires sample priors, which can be included via deep learning (DL). State-of-the-art 4D reconstruction methods for x-ray imaging combine the power of artificial intelligence and the physics of x-ray propagation to tackle the challenge of sparse views. However, most approaches do not constrain the physics of the studied process, i.e. a full physical model. Here we present 4D physics-informed optimized neural implicit x-ray imaging, a novel physics-informed 4D x-ray image reconstruction method combining the full physical model and a state-of-the-art DL-based reconstruction method for 4D x-ray imaging from sparse views. We demonstrate and evaluate the potential of our approach by retrieving 4D information from ultra-sparse spatiotemporal acquisitions of simulated binary droplet collisions, a relevant fluid dynamic process. We envision that this work will open new spatiotemporal possibilities for various 4D x-ray imaging modalities, such as time-resolved x-ray tomography and more novel sparse acquisition approaches like x-ray multi-projection imaging, which will pave the way for investigations of various rapid 4D dynamics, such as fluid dynamics and composite testing.</p>}},
  author       = {{Yao, Zisheng and Zhang, Yuhe and Hu, Zhe and Klöfkorn, Robert and Ritschel, Tobias and Villanueva-Perez, Pablo}},
  issn         = {{0957-0233}},
  keywords     = {{deep learning; four-dimensional (4D) reconstruction; physics-informed; ultra-sparse spatiotemporal data; ultrafast x-ray imaging}},
  language     = {{eng}},
  month        = {{08}},
  number       = {{8}},
  publisher    = {{IOP Publishing}},
  series       = {{Measurement Science and Technology}},
  title        = {{Physics-informed 4D x-ray image reconstruction from ultra-sparse spatiotemporal data}},
  url          = {{http://dx.doi.org/10.1088/1361-6501/adf2c9}},
  doi          = {{10.1088/1361-6501/adf2c9}},
  volume       = {{36}},
  year         = {{2025}},
}