Adorym: A multi-platform generic x-ray image reconstruction framework based on automatic differentiation

Abstract

We describe and demonstrate an optimization-based x-ray image reconstruction framework called Adorym. Our framework provides a generic forward model, allowing one code framework to be used for a wide range of imaging methods ranging from near-field holography to and fly-scan ptychographic tomography. By using automatic differentiation for optimization, Adorym has the flexibility to refine experimental parameters including probe positions, multiple hologram alignment, and object tilts. It is written with strong support for parallel processing, allowing large datasets to be processed on high-performance computing systems. We demonstrate its use on several experimental datasets to show improved image quality through parameter refinement.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• The NumPy array: a structure for efficient numerical computation
• An overview of gradient descent optimization algorithms
• X-ray image reconstruction from a diffraction pattern alone
• A unified evaluation of iterative projection algorithms for phase retrieval
• A Review of automatic differentiation and its efficient implementation
• Using Automatic Differentiation as a General Framework for Ptychographic Reconstruction
• Deep Learning with Dynamic Computation Graphs
• Regularized Newton Methods for X-ray Phase Contrast and General Imaging Problems
• Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
• Three dimensions, two microscopes, one code: automatic differentiation for x-ray nanotomography beyond the depth of focus limit
• Near, far, wherever you are: simulations on the dose efficiency of holographic and ptychographic coherent imaging

Cited by in corpus (7)

• A parameter refinement method for Ptychography based on Deep Learning concepts
• PtyRAD: A High-performance and Flexible Ptychographic Reconstruction Framework with Automatic Differentiation
• Dose-efficient Automatic Differentiation for Ptychographic Reconstruction
• Using a modified double deep image prior for crosstalk mitigation in multislice ptychography
• Electron Ptychography Reveals Correlated Lattice Vibrations at Atomic Resolution
• Multislice forward modeling of Coherent Surface Scattering Imaging on surface and interfacial structures
• A matrix-free Levenberg-Marquardt algorithm for efficient ptychographic phase retrieval