Super-resolution x-ray fluorescence microscopy using channel attention networks

Xiaoyin Zheng; Varun R. Kankanallu; Yu-Chen K. Chen-Wiegart; Xiaojing Huang

doi:10.1117/12.2680335

6 October 2023 Super-resolution x-ray fluorescence microscopy using channel attention networks

Xiaoyin Zheng, Varun R. Kankanallu, Yu-Chen K. Chen-Wiegart, Xiaojing Huang

Proceedings Volume PC12698, X-Ray Nanoimaging: Instruments and Methods VI; PC1269802 (2023) https://doi.org/10.1117/12.2680335
Event: SPIE Optical Engineering + Applications, 2023, San Diego, California, United States

Abstract

X-ray fluorescence (XRF) nanoimaging is a powerful technique to quantify the distribution of elements at the nanoscale. Typically, its spatial resolution is inherently limited by the probe profile and the scanning step size. The deep residual channel attention networks (RCAN) have been developed to enhance the resolution of natural images. In this work, we adapted RCAN to decouple the blurry impact from data acquisition and improve the resolution of XRF images. The performance was further enhanced by refining the network with a relatively small amount of experimental XRF images using a synchrotron nanoprobe. This refined network was then applied to study battery cathode materials, and the enhanced XRF images revealed finer structural and elemental details for a better understanding of their electrochemical reaction mechanism.

Conference Presentation

Citation Download Citation

Xiaoyin Zheng, Varun R. Kankanallu, Yu-Chen K. Chen-Wiegart, and Xiaojing Huang "Super-resolution x-ray fluorescence microscopy using channel attention networks", Proc. SPIE PC12698, X-Ray Nanoimaging: Instruments and Methods VI, PC1269802 (6 October 2023); https://doi.org/10.1117/12.2680335

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available