Deep Learning Coherent Diffractive Imaging

2022/04/18 by Dillan J. Chang, Colum M. O’Leary, Chang, Dillan J. +13
Biochemistry, Genetics and Molecular Biology · Physics and Astronomy · #Advanced Electron Microscopy Techniques and Applications #Digital Holography and Microscopy #Advanced X-ray Imaging Techniques

paper · pdf · doi:10.48550/arxiv.2204.08157

Abstract

We report the development of deep learning coherent electron diffractive imaging at sub-angstrom resolution using convolutional neural networks (CNNs) trained with only simulated data. We experimentally demonstrate this method by applying the trained CNNs to directly recover the phase images from electron diffraction patterns of twisted hexagonal boron nitride, monolayer graphene and a Au nanoparticle with comparable quality to those reconstructed by a conventional ptychographic method. Fourier ring correlation between the CNN and ptychographic images indicates the achievement of a spatial resolution in the range of 0.70 and 0.55 angstrom (depending on different resolution criteria). The ability to replace iterative algorithms with CNNs and perform real-time imaging from coherent diffraction patterns is expected to find broad applications in the physical and biological sciences.

Related

• Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction
• Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns
• Phase Retrieval of Highly Strained Bragg Coherent Diffraction Patterns using Supervised Convolutional Neural Network
• Sub-photon accuracy noise reduction of single shot coherent diffraction pattern with atomic model trained autoencoder
• AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging