Physics-Guided Deep Learning For High Resolution X-ray Imaging

TL;DR

This paper introduces a physics-guided deep learning method using U-Net to improve high-resolution X-ray imaging by effectively suppressing artifacts and preserving signals in challenging experimental conditions.

Contribution

It presents a novel deep learning approach that models artifacts explicitly and compares favorably against traditional filtering methods in X-ray image reconstruction.

Findings

Significant SSIM improvements from 0.345 to 0.906 and 0.0679 to 0.945.

Better filament profile preservation and reduced signal degradation.

Deep ensembles provide uncertainty estimates for robustness.

Abstract

Imperfections in X-ray imaging systems can limit their performance, especially in High Energy Density (HED) or Inertial Fusion Energy (IFE)-relevant experiments that are typically single shot, by introducing structured, non-stationary features that overlap with the signal of interest. When the X-ray transmission is reconstructed by typical flat-field normalization, even small shot-to-shot drift of structured features imprints residual patterns onto transmission maps, degrading signal visibility and biasing measurements such as electron density, velocity and feature sizes. We investigate this limitation by modeling the artifacts as a separable feature layer and training a U-Net architecture to estimate and infer them directly from the experimental data. We compare our method against Fourier filtering and more advanced procedures like Dynamic Flat-Field Normalization (DFFN) to evaluate artifact suppression capability and signal preservation in the reconstructed transmission maps. In multiple synthetic injection tests, our Physics-Guided Deep Learning approach is able to obtain an improvement in mean Structural Similarity Index (SSIM) from 0.345 to 0.906 and from 0.0679 to 0.945, while better preserving filament profiles and reducing degradation of the filament signal during artifact suppression. Additionally, we utilize deep ensembles to obtain predictive epistemic uncertainty estimates for the U-Net based reconstruction, to ensure Out Of Distribution (OOD) robustness for this procedure.