Deep learning enables nanoscale X-ray 3D imaging with limited data

Chonghang Zhao; Hanfei Yan

doi:10.1038/s41377-023-01198-z

Deep learning enables nanoscale X-ray 3D imaging with limited data

Light Sci Appl. 2023 Jun 27;12(1):159. doi: 10.1038/s41377-023-01198-z.

Authors

Chonghang Zhao¹, Hanfei Yan²

Affiliations

¹ National Synchrotron Light Source II, Brookhaven National Laboratory, Upton, NY, 11973, USA.
² National Synchrotron Light Source II, Brookhaven National Laboratory, Upton, NY, 11973, USA. hyan@bnl.gov.

Abstract

Deep neural network can greatly improve tomography reconstruction with limited data. A recent effort of combining ptycho-tomography model with the 3D U-net demonstrated a significant reduction in both the number of projections and computation time, and showed its potential for integrated circuit imaging that requires high-resolution and fast measurement speed.