Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

AI-Powered MRI Radiomics and Deep Learning for Preoperative Prediction of Cavernous Sinus Invasion in Pituitary Adenomas: A Clinically Oriented Review of Current Evidence.

Neuroimage. Reports·2026
Same author

Supervised Volumetric Segmentation of White and Gray Matter from Brain Positron Emission Tomography Images Using Magnetic Resonance Labels.

Journal of medical signals and sensors·2026
Same author

Swin UNETR-based prediction of [<sup>68</sup>Ga]Ga-FAPI-46 PET/CT dose rate maps in cancer patients: quantitative comparison with [<sup>18</sup>F]FDG PET/CT.

BMC medical imaging·2026
Same author

Revisiting multi-nodal radiomics with advanced feature learning for lymphoma classification: a multi-center study.

Physics in medicine and biology·2026
Same author

Clinically reliable and stable automated segmentation of DLBCL lesions on PET/CT using self-configuring nnU-Net for robust TMTV quantification.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026
Same author

FAP-Targeted Theranostics in Advanced Sarcoma: A Pilot Study of ⁶⁸Ga-FAPI-46 Imaging and ¹⁷⁷Lu-FAPI-2286 Therapy.

Clinical nuclear medicine·2026
Same journal

Preoperative breast MRI and long-term survival in ductal carcinoma in situ: a propensity score-weighted analysis.

European radiology·2026
Same journal

Efficacy evaluation of artificial intelligence in radiological imaging diagnosis based on randomized controlled trials: a scoping review.

European radiology·2026
Same journal

The bMRI-QUAL scoring system: an important first step toward standardizing breast MRI quality.

European radiology·2026
Same journal

Spectral CT-based habitat analysis for predicting pathologic response to neoadjuvant therapy in gastric cancer.

European radiology·2026
Same journal

MR-guided microwave ablation of liver tumors: outcomes in local tumor control and determinants of treatment success.

European radiology·2026
Same journal

AI integration in pediatric radiology: perspectives from international academic leaders.

European radiology·2026
See all related articles

Related Experiment Video

Updated: Nov 17, 2025

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences
08:19

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences

Published on: May 17, 2018

10.1K

Deep learning-based metal artefact reduction in PET/CT imaging.

Hossein Arabi1, Habib Zaidi2,3,4,5

  • 1Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva 4, Switzerland.

European Radiology
|February 11, 2021
PubMed
Summary
This summary is machine-generated.

Deep learning-based metal artefact reduction (MAR) in the image domain (DLI-MAR) significantly improves quantitative PET/CT imaging by reducing artefacts from metallic implants. This technique generates accurate CT-based attenuation maps, minimizing bias in PET images.

Keywords:
ArtefactsArtificial intelligenceComputed X-ray tomographyDeep learningPositron emission tomography

More Related Videos

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

10.1K
DUCT: Double Resin Casting followed by Micro-Computed Tomography for 3D Liver Analysis
12:39

DUCT: Double Resin Casting followed by Micro-Computed Tomography for 3D Liver Analysis

Published on: September 28, 2021

3.5K

Related Experiment Videos

Last Updated: Nov 17, 2025

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences
08:19

Protocol for the Evaluation of MRI Artifacts Caused by Metal Implants to Assess the Suitability of Implants and the Vulnerability of Pulse Sequences

Published on: May 17, 2018

10.1K
3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography
07:01

3D Imaging of Soft-Tissue Samples using an X-ray Specific Staining Method and Nanoscopic Computed Tomography

Published on: October 24, 2019

10.1K
DUCT: Double Resin Casting followed by Micro-Computed Tomography for 3D Liver Analysis
12:39

DUCT: Double Resin Casting followed by Micro-Computed Tomography for 3D Liver Analysis

Published on: September 28, 2021

3.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiological Physics

Background:

  • Metallic implants in patients undergoing PET/CT scans cause significant artifacts in CT images due to beam hardening and photon starvation.
  • These metal-induced artifacts lead to inaccurate CT-based attenuation correction (AC) in PET imaging, resulting in quantitative bias and image degradation.
  • Existing metal artifact reduction (MAR) methods often struggle to fully correct these distortions, impacting diagnostic accuracy.

Purpose of the Study:

  • To investigate the efficacy of deep learning-based metal artifact reduction (MAR) techniques for quantitative PET/CT imaging.
  • To compare MAR methods implemented in the image domain (DLI-MAR) and projection domain (DLP-MAR) against a normalized MAR (NMAR) approach.
  • To assess the impact of MAR on the accuracy of CT-based attenuation and scatter correction in the presence of metallic implants.

Main Methods:

  • Developed and implemented deep learning-based MAR algorithms in both the image (DLI-MAR) and projection (DLP-MAR) domains.
  • Quantitatively evaluated the performance of DLI-MAR and DLP-MAR against NMAR using simulated metal artifacts on 80 metal-free CT images.
  • Clinically validated the MAR techniques on 30 retrospective 18F-FDG PET/CT datasets affected by metallic implants.

Main Results:

  • DLI-MAR demonstrated superior performance in minimizing CT metal artifacts, achieving a structural similarity (SSIM) of 0.95 ± 0.2, compared to DLP-MAR (0.94 ± 0.2) and NMAR (0.93 ± 0.3).
  • Metal artifacts in CT images and AC maps introduced significant quantitative bias and under/overestimation of scatter correction in PET images.
  • The DLI-MAR technique reduced quantitative PET bias to 1.3 ± 3%, a substantial improvement over no MAR (10.5 ± 6%) and NMAR (3.2 ± 0.5%).

Conclusions:

  • Deep learning-based MAR in the image domain (DLI-MAR) effectively reduces adverse metal artifacts in CT images.
  • Accurate attenuation maps generated by DLI-MAR from corrupted CT images significantly mitigate the impact of metal artifacts on quantitative PET/CT imaging.
  • The DLI-MAR technique shows significant potential for improving the accuracy and reliability of quantitative PET/CT analyses in patients with metallic implants.