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

Early timepoint <sup>99m</sup>Tc-DPD whole body scintigraphy and quantitative SPECT/CT imaging for diagnosis of cardiac ATTR amyloidosis.

EJNMMI research·2026
Same author

Multicentre Validation of the 2019 Briganti Nomogram: One Threshold Does Not Fit All.

International braz j urol : official journal of the Brazilian Society of Urology·2026
Same author

Active Brown Adipose Tissue Is Associated With Reduced Arterial Inflammation and Less Atherogenic Circulating Factors in Individuals With Obesity.

Arteriosclerosis, thrombosis, and vascular biology·2026
Same author

Semi-quantitative evaluation of early phase <sup>99m</sup>Tc-DPD scintigraphy in patients with suspected cardiac amyloidosis.

Annals of nuclear medicine·2026
Same author

Brain Metabolic Activity Measured by [<sup>18</sup>F]FDG PET/CT Predicts Survival in Patients with Advanced Non-Small Cell Lung Cancer.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

[<sup>18</sup>F]FDG PET/CT multiomics identifies Hedgehog-driven HPV-negative head and neck squamous cell carcinoma.

Molecular cancer·2026
Same journal

Subcortical dopamine D<sub>2</sub> receptor availability and glucose metabolism in autism: a dual-tracer PET/MR study.

European journal of nuclear medicine and molecular imaging·2026
Same journal

PET-based assessment of coronary microvascular dysfunction and its relation to plaque burden and vascular remodeling: integration with microvascular resistance reserve.

European journal of nuclear medicine and molecular imaging·2026
Same journal

Efficacy of peptide receptor radionuclide therapy in patients with oligodiscordant gastroenteropancreatic neuroendocrine tumours.

European journal of nuclear medicine and molecular imaging·2026
Same journal

PET imaging of atherosclerotic plaques using the stabilin-2-targeted tracer <sup>18</sup>F-S2P in preclinical models.

European journal of nuclear medicine and molecular imaging·2026
Same journal

Glucagon-like peptide-1 receptor PET in indolent and aggressive insulinoma: Diagnostic performance, quantitative differences, and clinical implications.

European journal of nuclear medicine and molecular imaging·2026
Same journal

AI-based tumor and organ volumetry predicts early progression after Y-90 radioembolization in liver-dominant metastatic disease.

European journal of nuclear medicine and molecular imaging·2026
See all related articles

Related Experiment Video

Updated: Jun 27, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K

Multicenter PET image harmonization using generative adversarial networks.

David Haberl1, Clemens P Spielvogel1,2, Zewen Jiang1,2

  • 1Division of Nuclear Medicine, Medical University of Vienna, Währinger Gürtel 18-20/E4L, A-1090, Vienna, Austria.

European Journal of Nuclear Medicine and Molecular Imaging
|May 2, 2024
PubMed
Summary
This summary is machine-generated.

Cycle-consistent generative adversarial networks (GANs) harmonize PET scans across centers, improving radiomic feature reproducibility and predictive performance in cancer studies. This approach enhances data consistency for multicentric research.

Keywords:
Deep learningGenerative adversarial networksHarmonizationMulticenterQuantitative PET

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

393
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

583

Related Experiment Videos

Last Updated: Jun 27, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

393
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

583

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiomics

Background:

  • Multicentric Positron Emission Tomography (PET) studies face challenges in radiomic feature reproducibility due to variations in scanners and protocols.
  • Harmonization techniques are crucial for standardizing PET data across different institutions to enable reliable analysis.
  • Generative Adversarial Networks (GANs) offer potential for image style and texture translation, but their application in PET harmonization requires evaluation.

Purpose of the Study:

  • To develop and evaluate cycle-consistent Generative Adversarial Network (GAN) harmonization for improving PET radiomic feature reproducibility and predictive performance in multicentric studies.
  • To assess the impact of GAN-harmonization on image quality and feature consistency across different centers and scanners.

Main Methods:

  • Developed a GAN-harmonization technique for whole-body PET scan style and texture translation between centers and scanners.
  • Applied GAN-harmonization to a dual-center lung cancer cohort to evaluate radiomic feature reproducibility in liver tissue.
  • Utilized a head and neck cancer cohort from three centers to analyze the clinical impact of GAN-harmonization on predicting distant metastases using logistic regression with radiomic features.

Main Results:

  • Image quality was maintained post-harmonization, with structural similarity scores above 0.780 across various organs.
  • GAN-harmonization significantly increased inter-site reproducibility of radiomic features in liver tissue, with improvements ranging from 5% to 23% across different feature types.
  • In the head and neck cancer cohort, GAN-harmonization improved the predictive performance for distant metastases, increasing the Area Under the Curve (AUC) from 0.68 to 0.73.

Conclusions:

  • Cycle-consistent GANs effectively perform image harmonization for PET scans, enhancing data consistency across multicentric studies.
  • GAN-based harmonization significantly improves the reproducibility of radiomic features and the predictive performance of clinical outcome models.
  • This approach holds promise for advancing multicentric PET research by reducing site-specific variations and increasing the reliability of radiomic analyses.