Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram

Journal Article · · Optics Express
DOI:https://doi.org/10.1364/oe.569216· OSTI ID:2589748
 [1];  [2];  [2];  [2];  [2];  [2];  [1];  [3];  [4];  [2];  [2]
  1. Brookhaven National Laboratory (BNL), Upton, NY (United States). National Synchrotron Light Source II (NSLS-II)
  2. Helmholtz-Zentrum Hereon, Geesthacht (Germany)
  3. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany)
  4. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany); Univ. of Hamburg (Germany)
+ Show Author Affiliations
X-ray phase contrast imaging significantly improves the visualization of structures with weak or uniform absorption, broadening its applications across a wide range of scientific disciplines. Propagation-based phase contrast is particularly suitable for time- or dose-critical in vivo/in situ/operando (tomography) experiments because it requires only a single intensity measurement. However, the phase information of the wave field is lost during the measurement and must be recovered. Conventional algebraic and iterative methods often rely on specific approximations or boundary conditions that may not be met by many samples or experimental setups. In addition, they require manual tuning of reconstruction parameters by experts, making them less adaptable for complex or variable conditions. Here we present a self-learning approach for solving the inverse problem of phase retrieval in the near-field regime of Fresnel theory using a single intensity measurement (hologram). A physics-informed generative adversarial network is employed to reconstruct both the phase and absorbance of the unpropagated wave field in the sample plane from a single hologram. Unlike most state-of-the-art deep learning approaches for phase retrieval, our approach does not require paired, unpaired, or simulated training data. This significantly broadens the applicability of our approach, as acquiring or generating suitable training data remains a major challenge due to the wide variability in sample types and experimental configurations. The algorithm demonstrates robust and consistent performance across diverse imaging conditions and sample types, delivering quantitative, high-quality reconstructions for both simulated data and experimental datasets acquired at beamline P05 at PETRA III (DESY, Hamburg), operated by Helmholtz-Zentrum Hereon. Furthermore, it enables the simultaneous retrieval of both phase and absorption information.
Research Organization:
Brookhaven National Laboratory (BNL), Upton, NY (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)
Grant/Contract Number:
SC0012704
OSTI ID:
2589748
Report Number(s):
BNL--228972-2025-JAAM
Journal Information:
Optics Express, Journal Name: Optics Express Journal Issue: 17 Vol. 33; ISSN 1094-4087
Publisher:
Optica Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (64)

Propagation‐Based Phase Contrast Computed Tomography as a Suitable Tool for the Characterization of Spatial 3D Cell Distribution in Biomaterials journal May 2021
Deep Image Prior journal March 2020
Quantitative susceptibility mapping through model-based deep image prior (MoDIP) journal May 2024
A New Microscopic Principle journal May 1948
Phase-contrast imaging of weakly absorbing materials using hard X-rays journal February 1995
Phase-contrast imaging using polychromatic hard X-rays journal November 1996
Phase recovery and holographic image reconstruction using deep learning in neural networks journal October 2017
Phase retrieval and differential phase-contrast imaging with low-brilliance X-ray sources journal March 2006
Bright-field holography: cross-modality deep learning enables snapshot 3D imaging with bright-field contrast using a single hologram journal March 2019
Deep learning in holography and coherent imaging journal September 2019
Phase imaging with an untrained neural network journal May 2020
On the use of deep learning for phase recovery journal January 2024
Quantitative phase imaging based on holography: trends and new perspectives journal June 2024
AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging journal June 2022
Artificial intelligence-enabled quantitative phase imaging methods for life sciences journal October 2023
Propagation-based phase-contrast synchrotron imaging of aortic dissection in mice: from individual elastic lamella to 3D analysis journal February 2018
Multi-resolution convolutional neural networks for inverse problems journal March 2020
Self-supervised learning of hologram reconstruction using physics consistency journal August 2023
Simultaneous phase and amplitude extraction from a single defocused image of a homogeneous object journal April 2002
Holotomography: Quantitative phase tomography with micrometer resolution using hard synchrotron radiation x rays journal November 1999
Phase‐Sensitive X‐Ray Imaging journal July 2000
A coded-aperture technique allowing x-ray phase contrast imaging with conventional sources journal August 2007
X-ray phase imaging with a paper analyzer journal March 2012
Micro-CT at the imaging beamline P05 at PETRA III
  • Wilde, Fabian; Ogurreck, Malte; Greving, Imke
  • PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON SYNCHROTRON RADIATION INSTRUMENTATION – SRI2015, AIP Conference Proceedings https://doi.org/10.1063/1.4952858
conference January 2016
Propagation based phase retrieval of simulated intensity measurements using artificial neural networks journal March 2018
Two-Dimensional X-Ray Beam Phase Sensing journal April 2012
Speckle-Based X-Ray Phase-Contrast and Dark-Field Imaging with a Laboratory Source journal June 2014
X-ray Phase-Contrast Imaging and Metrology through Unified Modulated Pattern Analysis journal May 2017
Hard-X-Ray Lensless Imaging of Extended Objects journal January 2007
TomoPy: a framework for the analysis of synchrotron tomographic data journal August 2014
Tomographic reconstruction with a generative adversarial network journal February 2020
Digital Holographic Reconstruction Based on Deep Learning Framework With Unpaired Data journal April 2020
Phase Retrieval with Application to Optical Imaging: A contemporary overview journal May 2015
Signal estimation from modified short-time Fourier transform journal April 1984
Deep Convolutional Neural Network for Inverse Problems in Imaging journal September 2017
Untrained Neural Network Priors for Inverse Imaging Problems: A Survey journal January 2022
High-Resolution Scanning X-ray Diffraction Microscopy journal July 2008
Demonstration of X-Ray Talbot Interferometry journal July 2003
Phase retrieval algorithms: a comparison journal January 1982
Digital simulation of scalar optical diffraction: revisiting chirp function sampling criteria and consequences journal January 2009
Irradiance moments: their propagation and use for unique retrieval of phase journal January 1982
Phase retrieval, error reduction algorithm, and Fienup variants: a view from convex optimization journal January 2002
Quantitative single-exposure x-ray phase contrast imaging using a single attenuation grid journal January 2011
eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction journal January 2018
Hard X-ray nano-holotomography with a Fresnel zone plate journal November 2020
PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets journal January 2021
DH-GAN: a physics-driven untrained generative adversarial network for holographic imaging journal March 2023
Artifact-suppressing reconstruction of strongly interacting objects in X-ray near-field holography without a spatial support constraint journal March 2024
Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram journal August 2025
Reconstruction of an object from the modulus of its Fourier transform journal January 1978
X-ray phase-attenuation duality and phase retrieval journal February 2005
Deep Gauss–Newton for phase retrieval journal February 2023
X-ray phase imaging: Demonstration of extended conditions with homogeneous objects journal January 2004
Lensless computational imaging through deep learning journal January 2017
High-resolution and sensitivity bi-directional x-ray phase contrast imaging using 2D Talbot array illuminators journal December 2021
Phase retrieval framework for direct reconstruction of the projected refractive index applied to ptychography and holography journal March 2022
Extended depth-of-field in holographic imaging using deep-learning-based autofocusing and phase recovery journal January 2018
Reliable deep-learning-based phase imaging with uncertainty quantification journal January 2019
Degradation Analysis of Thin Mg-xAg Wires Using X-ray Near-Field Holotomography journal September 2021
Adam: A Method for Stochastic Optimization preprint January 2014
Layer Normalization preprint January 2016
Image-to-Image Translation with Conditional Adversarial Networks preprint January 2016
prDeep: Robust Phase Retrieval with a Flexible Deep Network preprint January 2018
Phase retrieval for Fourier Ptychography under varying amount of measurements preprint January 2018

Similar Records

Micro-CT at the imaging beamline P05 at PETRA III
Journal Article · Wed Jul 27 00:00:00 EDT 2016 · AIP Conference Proceedings · OSTI ID:22608371
Improving the reconstruction quality with extension and apodization of the digital hologram
Journal Article · Mon Jun 01 00:00:00 EDT 2009 · Applied Optics · OSTI ID:22036375
Quantum volume hologram
Journal Article · Sun Feb 14 23:00:00 EST 2010 · Physical Review. A · OSTI ID:21408161

Related Subjects

36 MATERIALS SCIENCE