Uncertainty-guided Generation of Dark-field Radiographs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Felsner, Lina, Bast, Henriette, Dorosti, Tina, Schaff, Florian, Pfeiffer, Franz, Pfeiffer, Daniela, Schnabel, Julia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908781503315968
author Felsner, Lina
Bast, Henriette
Dorosti, Tina
Schaff, Florian
Pfeiffer, Franz
Pfeiffer, Daniela
Schnabel, Julia
author_facet Felsner, Lina
Bast, Henriette
Dorosti, Tina
Schaff, Florian
Pfeiffer, Franz
Pfeiffer, Daniela
Schnabel, Julia
contents X-ray dark-field radiography provides complementary diagnostic information to conventional attenuation imaging by visualizing microstructural tissue changes through small-angle scattering. However, the limited availability of such data poses challenges for developing robust deep learning models. In this work, we present the first framework for generating dark-field images directly from standard attenuation chest X-rays using an Uncertainty-Guided Progressive Generative Adversarial Network. The model incorporates both aleatoric and epistemic uncertainty to improve interpretability and reliability. Experiments demonstrate high structural fidelity of the generated images, with consistent improvement of quantitative metrics across stages. Furthermore, out-of-distribution evaluation confirms that the proposed model generalizes well. Our results indicate that uncertainty-guided generative modeling enables realistic dark-field image synthesis and provides a reliable foundation for future clinical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15859
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Uncertainty-guided Generation of Dark-field Radiographs
Felsner, Lina
Bast, Henriette
Dorosti, Tina
Schaff, Florian
Pfeiffer, Franz
Pfeiffer, Daniela
Schnabel, Julia
Machine Learning
Computer Vision and Pattern Recognition
X-ray dark-field radiography provides complementary diagnostic information to conventional attenuation imaging by visualizing microstructural tissue changes through small-angle scattering. However, the limited availability of such data poses challenges for developing robust deep learning models. In this work, we present the first framework for generating dark-field images directly from standard attenuation chest X-rays using an Uncertainty-Guided Progressive Generative Adversarial Network. The model incorporates both aleatoric and epistemic uncertainty to improve interpretability and reliability. Experiments demonstrate high structural fidelity of the generated images, with consistent improvement of quantitative metrics across stages. Furthermore, out-of-distribution evaluation confirms that the proposed model generalizes well. Our results indicate that uncertainty-guided generative modeling enables realistic dark-field image synthesis and provides a reliable foundation for future clinical applications.
title Uncertainty-guided Generation of Dark-field Radiographs
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15859