TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Dual-domain artifact disentanglement for metal artifact reduction in CT images
 
Options

Dual-domain artifact disentanglement for metal artifact reduction in CT images

Publikationstyp
Conference Paper
Date Issued
2026-04-03
Sprache
English
Author(s)
Rudloff, Adrian  
Medizintechnische und Intelligente Systeme E-1  
Lugas, Dovydas  
Latus, Sarah  orcid-logo
Medizintechnische und Intelligente Systeme E-1  
Paulauskaitė-Tarasevičienė, Agnė
Šutiene, Kristina
Schlaefer, Alexander  
Medizintechnische und Intelligente Systeme E-1  
TORE-URI
https://hdl.handle.net/11420/63193
First published in
Proceedings of SPIE  
Number in series
13925
Citation
SPIE Medical Imaging 2026
Contribution to Conference
SPIE Medical Imaging 2026  
Publisher DOI
10.1117/12.3085638
Scopus ID
2-s2.0-105039315118
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
Funding(s)
Centre of Excellence of Al for Sustainable Living and Working  
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback