Phase Retrieval of Highly Strained Bragg Coherent Diffraction Patterns using Supervised Convolutional Neural Network

TL;DR

This paper introduces a supervised CNN approach for phase retrieval in highly strained Bragg coherent diffraction patterns, outperforming traditional iterative algorithms on simulated and experimental data.

Contribution

The novel use of a supervised CNN trained on simulated data effectively retrieves phases in highly strained crystals, surpassing standard methods.

Findings

CNN outperforms standard algorithms on simulated data

Model successfully applies to experimental data

Enhanced phase retrieval for highly strained crystals

Abstract

In Bragg Coherent Diffraction Imaging (BCDI), Phase Retrieval of highly strained crystals is often challenging with standard iterative algorithms. This computational obstacle limits the potential of the technique as it precludes the reconstruction of physically interesting highly-strained particles. Here, we propose a novel approach to this problem using a supervised Convolutional Neural Network (CNN) trained on 3D simulated diffraction data to predict the corresponding reciprocal space phase. This method allows to fully exploit the potential of the CNN by mapping functions within the same space and leveraging structural similarities between input and output. The final object is obtained by the inverse Fourier transform of the retrieved complex diffracted amplitude and is then further refined with iterative algorithms. We demonstrate that our model outperforms standard algorithms on highly strained simulated data not included in the training set, as well as on experimental data.