Options
Dual-domain artifact disentanglement for metal artifact reduction in CT images
Publikationstyp
Conference Paper
Date Issued
2026-04-03
Sprache
English
Author(s)
Paulauskaitė-Tarasevičienė, Agnė
Šutiene, Kristina
First published in
Number in series
13925
Citation
SPIE Medical Imaging 2026
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
SPIE
Medical diagnosis from Computed Tomography (CT) often suffers from artifacts caused by high-density materials like metal implants. Metal Artifact Reduction (MAR) remains a challenge which has been addressed using deep learning. Supervised learning methods for MAR traditionally require paired scans with and without metal - a requirement rarely met in practice. Unsupervised approaches such as the Artifact Disentanglement Network (ADN) learn from unpaired data, while Variational Autoencoders (VAE) reconstruct artifact-free images via latent representations. Dual-domain methods have been proposed, combining image and sinogram data to exploit the localization of metal artifacts in Radon domain for improved reduction. This study evaluates (1) using VAE as a baseline, (2) performing disentanglement of ADN solely in Radon domain, and (3) integrating Cartesian and Radon features into ADN. Experiments on synthetic and clinical data show ADN outperforms VAE, and our dual-domain approach RadonADN further improves results, achieving an SSIM of 0.92 versus 0.91 without Radon domain information, demonstrating the benefit of incorporating the sinogram representation.
Subjects
Metal Artifact Reduction
Computer Tomography
Unsupervised Learning
Dual-Domain
DDC Class
620: Engineering