EUVIMEDEUVIMED entdecken
Crossref

Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network

Xiaoyin Zheng, Varun R. Kankanallu, Chang-An Lo, Ajith Pattammattel, Yong Chu, Yu-Chen Karen Chen-Wiegart, Xiaojing Huang

Optica · 20.02.2024 · 11 (2) · 146

DOI: 10.1364/optica.503398 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optica, online erschienen am 25.01.2024. Verfasst von Xiaoyin Zheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: U.S. Department of Energy, Office of Science, Basic Energy Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

X-ray fluorescence (XRF) microscopy is a powerful technique for quantifying the distribution of elements in complex materials, which makes it a crucial imaging technique across a wide range of disciplines in physical and biological sciences, including chemistry, materials science, microbiology, and geosciences. However, as a scanning microscopy technique, the spatial resolution of XRF imaging is inherently constrained by the x-ray probe profile and scanning step size. Here we propose a dual-branch machine learning (ML) model, which can extract scale-variant features and bypass abundant low-frequency information separately, to enhance the spatial resolution of the XRF images by mitigating the effects of blurring from the probe profile. The model is trained by simulated natural images, and a two-stage training strategy is used to overcome the domain gap between the natural images and experimental data. The tomography reconstruction from enhanced XRF projections shows an improvement in resolution by a scale factor of four and reveals distinct internal features invisible in low-resolution XRF within a battery sample. This study offers a promising approach for obtaining high-resolution XRF imaging from its low-resolution version, paving the way for future investigations in a broader range of disciplines and materials.

Förderung

  • U.S. Department of Energy, Office of Science, Basic Energy Sciences

Zitieren

APA

Zheng, X., Kankanallu, V. R., Lo, C., Pattammattel, A., Chu, Y., Chen-Wiegart, Y. K., & Huang, X. (2024). Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network. Optica, 11(2), 146. https://doi.org/10.1364/optica.503398

Vancouver

Zheng X, Kankanallu VR, Lo C, Pattammattel A, Chu Y, Chen-Wiegart YK, et al. Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network. Optica. 2024;11(2):146. doi:10.1364/optica.503398

BibTeX
@article{Zheng2024,
  author = {Zheng, Xiaoyin and Kankanallu, Varun R. and Lo, Chang-An and Pattammattel, Ajith and Chu, Yong and Chen-Wiegart, Yu-Chen Karen and Huang, Xiaojing},
  title = {Deep learning enhanced super-resolution x-ray fluorescence microscopy by a dual-branch network},
  journal = {Optica},
  year = {2024},
  volume = {11},
  number = {2},
  pages = {146},
  doi = {10.1364/optica.503398}
}
Kostenlos starten →