Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging

TL;DR

This paper introduces an adaptive 3D CNN-based method that reconstructs 3D crystals from coherent diffraction imaging by combining spherical harmonics representation with machine learning for improved accuracy.

Contribution

It proposes a novel adaptive approach integrating spherical harmonics and 3D CNNs for more accurate 3D crystal reconstruction from diffraction data.

Findings

Effective reconstruction of 3D crystals demonstrated

Adaptive feedback improves reconstruction accuracy

Spherical harmonics representation enhances model performance

Abstract

We present a novel adaptive machine-learning based approach for reconstructing three-dimensional (3D) crystals from coherent diffraction imaging (CDI). We represent the crystals using spherical harmonics (SH) and generate corresponding synthetic diffraction patterns. We utilize 3D convolutional neural networks (CNN) to learn a mapping between 3D diffraction volumes and the SH which describe the boundary of the physical volumes from which they were generated. We use the 3D CNN-predicted SH coefficients as the initial guesses which are then fine tuned using adaptive model independent feedback for improved accuracy.