EUVIMEDEUVIMED entdecken
Crossref

Accelerating iterative ptychography with an integrated neural network

Arthur R C McCray iD, Stephanie M Ribet, Georgios Varnavides, Colin Ophus

Journal of Microscopy · 2025-11 · 300 (2) · 180-190

DOI: 10.1111/jmi.13407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Microscopy, online erschienen am 07.04.2025. Verfasst von Arthur R C McCray und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Materials Science and Engineering, Stanford University, Stanford, California, USA. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Adolph C. and Mary Sprague Miller Institute for Basic Research in Science, University of California Berkeley, US Department of Energy Early Career Research Award, Office of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electron ptychography is a powerful and versatile tool for high‐resolution and dose‐efficient imaging. Iterative reconstruction algorithms are powerful but also computationally expensive due to their relative complexity and the many hyperparameters that must be optimised. Gradient descent‐based iterative ptychography is a popular method, but it may converge slowly when reconstructing low spatial frequencies. In this work, we present a method for accelerating a gradient descent‐based iterative reconstruction algorithm by training a neural network (NN) that is applied in the reconstruction loop. The NN works in Fourier space and selectively boosts low spatial frequencies, thus enabling faster convergence in a manner similar to accelerated gradient descent algorithms. We discuss the difficulties that arise when incorporating a NN into an iterative reconstruction algorithm and show how they can be overcome with iterative training. We apply our method to simulated and experimental data of gold nanoparticles on amorphous carbon and show that we can significantly speed up ptychographic reconstruction of the nanoparticles.

Schlagwörter

Stichwörter der Autor:innen

4DSTEMgradient descentmachine learningptychography

Autor:innen und Institutionen

  • Department of Materials Science and Engineering, Stanford University, Stanford, California, USA.
  • NCEM, Molecular Foundry, Lawrence Berkeley National Laboratory, Berkeley, California, USA.
  • Miller Institute for Basic Research in Science, University of California, Berkeley, California, USA.

ORCID-Profile: Arthur R C McCray

Förderung

  • Adolph C. and Mary Sprague Miller Institute for Basic Research in Science, University of California Berkeley
  • US Department of Energy Early Career Research Award
  • Office of Science
  • U.S. Department of Energy
  • National Energy Research Scientific Computing Center

Zitieren

APA

McCray, A. R. C., Ribet, S. M., Varnavides, G., & Ophus, C. (2025). Accelerating iterative ptychography with an integrated neural network. Journal of Microscopy, 300(2), 180-190. https://doi.org/10.1111/jmi.13407

Vancouver

McCray ARC, Ribet SM, Varnavides G, Ophus C. Accelerating iterative ptychography with an integrated neural network. Journal of Microscopy. 2025;300(2):180-190. doi:10.1111/jmi.13407

BibTeX
@article{McCray2025,
  author = {McCray, Arthur R C and Ribet, Stephanie M and Varnavides, Georgios and Ophus, Colin},
  title = {Accelerating iterative ptychography with an integrated neural network},
  journal = {Journal of Microscopy},
  year = {2025},
  volume = {300},
  number = {2},
  pages = {180--190},
  doi = {10.1111/jmi.13407}
}
Kostenlos starten →