AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging

TL;DR

AutoPhaseNN is a physics-informed deep learning model that efficiently solves the phase retrieval problem in 3D nanoscale imaging without labeled data, significantly reducing computation time while maintaining image quality.

Contribution

It introduces AutoPhaseNN, a novel unsupervised, physics-aware deep learning approach that learns to invert 3D BCDI data without requiring labeled datasets.

Findings

AutoPhaseNN is approximately 100 times faster than traditional methods.

It achieves comparable image quality to iterative phase retrieval.

The model learns from physics constraints without labeled real-space images.

Abstract

The problem of phase retrieval, or the algorithmic recovery of lost phase information from measured intensity alone, underlies various imaging methods from astronomy to nanoscale imaging. Traditional methods of phase retrieval are iterative in nature, and are therefore computationally expensive and time consuming. More recently, deep learning (DL) models have been developed to either provide learned priors to iterative phase retrieval or in some cases completely replace phase retrieval with networks that learn to recover the lost phase information from measured intensity alone. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on hundreds of or even thousands of experimental datasets. Using a 3D nanoscale X-ray imaging modality (Bragg Coherent Diffraction Imaging or BCDI) as a representative technique, we demonstrate AutoPhaseNN, a DL-based approach which learns to solve the phase problem without labeled data. By incorporating the physics of the imaging technique into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data from reciprocal space to real space in a single shot without ever being shown real space images. Once trained, AutoPhaseNN is about one hundred times faster than traditional iterative phase retrieval methods while providing comparable image quality.