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

Dosimetry and pharmacokinetics of [<sup>223</sup>Ra]Ra-dichloride alpha therapy in prostate cancer patients with bone metastases.

Physics in medicine and biology·2026
Same author

Fluid dynamics-informed CCTA-derived geometric parameters in right coronary artery anomalies predict abnormal invasive Adenosine-FFR and Dobutamine-FFR.

Computers in biology and medicine·2026
Same author

Operationalization drift in the construct of impulsivity: relevance to animal models of addiction.

Translational psychiatry·2026
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

Clinical and Cardiac Magnetic Resonance Phenotype of Probable Viral versus Probable Immune-mediated Acute Myocarditis.

European journal of heart failure·2026

Related Experiment Video

Updated: Aug 9, 2025

Non-invasive Imaging and Analysis of Cerebral Ischemia in Living Rats Using Positron Emission Tomography with 18F-FDG
10:31

Non-invasive Imaging and Analysis of Cerebral Ischemia in Living Rats Using Positron Emission Tomography with 18F-FDG

Published on: December 28, 2014

14.1K

A cycle-consistent adversarial network for brain PET partial volume correction without prior anatomical information.

Amirhossein Sanaat1, Hossein Shooli2, Andrew Stephen Böhringer1

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

European Journal of Nuclear Medicine and Molecular Imaging
|February 22, 2023
PubMed
Summary

A novel CycleGAN-based partial volume correction (PVC) technique effectively corrects Positron Emission Tomography (PET) images. This method enhances image quality without needing additional anatomical data, improving diagnostic accuracy for various radiotracers.

Keywords:
BrainDeep learningPETPartial volume correctionPartial volume effect

More Related Videos

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.9K
In vivo Positron Emission Tomography to Reveal Activity Patterns Induced by Deep Brain Stimulation in Rats
09:36

In vivo Positron Emission Tomography to Reveal Activity Patterns Induced by Deep Brain Stimulation in Rats

Published on: March 23, 2022

2.3K

Related Experiment Videos

Last Updated: Aug 9, 2025

Non-invasive Imaging and Analysis of Cerebral Ischemia in Living Rats Using Positron Emission Tomography with 18F-FDG
10:31

Non-invasive Imaging and Analysis of Cerebral Ischemia in Living Rats Using Positron Emission Tomography with 18F-FDG

Published on: December 28, 2014

14.1K
Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
07:57

Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform

Published on: March 24, 2022

2.9K
In vivo Positron Emission Tomography to Reveal Activity Patterns Induced by Deep Brain Stimulation in Rats
09:36

In vivo Positron Emission Tomography to Reveal Activity Patterns Induced by Deep Brain Stimulation in Rats

Published on: March 23, 2022

2.3K

Area of Science:

  • Medical Imaging
  • Nuclear Medicine
  • Artificial Intelligence in Healthcare

Background:

  • Partial volume effect (PVE) in Positron Emission Tomography (PET) arises from limited scanner resolution, causing inaccurate voxel intensity values.
  • PVE can lead to under- or overestimation of tracer uptake, potentially impacting diagnostic interpretations in clinical brain PET studies.
  • Existing partial volume correction (PVC) methods may require additional anatomical information or complex processing steps.

Purpose of the Study:

  • To develop and evaluate a novel, end-to-end CycleGAN-based partial volume correction (PVC) technique for brain PET images.
  • To overcome the adverse effects of partial volume effect (PVE) on PET image intensity values.
  • To assess the performance of the proposed PVC method across different radiotracers without relying on additional anatomical data.

Main Methods:

  • A CycleGAN model was trained to directly translate non-PVC PET images into PVC PET images.
  • The study utilized 212 clinical brain PET scans (18F-FDG, 18F-Flortaucipir, 18F-Flutemetamol, 18F-FluoroDOPA) and corresponding MRI scans.
  • Quantitative evaluation involved metrics like SSIM, RMSE, PSNR, Bland and Altman analysis, and radiomic feature analysis, comparing CycleGAN-derived PVC images against Iterative Yang-based PVC as reference.

Main Results:

  • The CycleGAN model generated PVC PET images with high fidelity, demonstrated by strong correlations in activity concentration and radiomic features compared to reference methods.
  • Quantitative metrics showed favorable performance across different radiotracers, with 18F-Flutemetamol yielding the highest PSNR and SSIM, and 18F-FDG showing the largest variance in Bland and Altman analysis.
  • Radiomic analysis indicated low average relative errors for key features, suggesting the preservation of quantitative information post-correction.

Conclusions:

  • The developed end-to-end CycleGAN PVC method effectively corrects PVE in brain PET images.
  • This approach eliminates the need for additional anatomical information (MRI/CT), accurate registration, segmentation, or scanner characterization.
  • The CycleGAN PVC method offers a promising, automated solution for improving the quantitative accuracy and diagnostic utility of PET imaging.