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 Experiment Video

Updated: Dec 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

938

PET image super-resolution using generative adversarial networks.

Tzu-An Song1, Samadrita Roy Chowdhury1, Fan Yang1

  • 1Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA, United States of America.

Neural Networks : the Official Journal of the International Neural Network Society
|February 21, 2020
PubMed
Summary

Related Concept Videos

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

12.1K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
12.1K

You might also read

Related Articles

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

Sort by
Same author

Surface substance loss of subsurface bovine enamel lesions after different steps of the resinous infiltration technique: a 3D topography analysis.

Odontology·2011
Same author

Expression of IL-23/Th17 pathway in a murine model of Coxsackie virus B3-induced viral myocarditis.

Virology journal·2011
Same author

Extracellular matrix peptides of Artemia cyst shell participate in protecting encysted embryos from extreme environments.

PloS one·2011
Same author

Therapeutic effect of carboxymethylated and quanternized chitosan on insulin resistance in high-fat-diet-induced rats and 3T3-L1 adipocytes.

Journal of biomaterials science. Polymer edition·2011
Same author

Role of reactive oxygen species in triptolide-induced apoptosis of renal tubular cells and renal injury in rats.

Journal of Huazhong University of Science and Technology. Medical sciences = Hua zhong ke ji da xue xue bao. Yi xue Ying De wen ban = Huazhong keji daxue xuebao. Yixue Yingdewen ban·2011
Same author

Chlorination and ortho-acetoxylation of 2-arylbenzoxazoles.

Organic & biomolecular chemistry·2011
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles
This summary is machine-generated.

This study introduces a self-supervised super-resolution (SSSR) technique for positron emission tomography (PET) using dual generative adversarial networks (GANs). This method enhances PET image quality without requiring paired low- and high-resolution data, improving clinical applicability.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Image Processing

Background:

  • Positron emission tomography (PET) suffers from low spatial resolution, impacting image quality and quantitative accuracy.
  • Existing supervised super-resolution (SR) methods for PET require paired low- and high-resolution training data, which are often unavailable in clinical settings.

Purpose of the Study:

  • To develop a self-supervised super-resolution (SSSR) technique for PET imaging that does not require paired training data.
  • To improve the spatial resolution and image quality of PET scans for enhanced quantitation and clinical applicability.

Main Methods:

  • A novel SSSR technique employing dual generative adversarial networks (GANs) was developed.
  • The network integrates low-resolution PET, high-resolution MRI, spatial coordinates, and features from a supervised auxiliary CNN trained on simulated data.
Keywords:
CNNGANMultimodality imagingPETSelf-supervisedSuper-resolution

Related Experiment Videos

Last Updated: Dec 28, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

938
  • Training utilizes a loss function incorporating adversarial losses, cycle consistency, and total variation penalty.

    • Main Results:

    • The SSSR technique was validated on a clinical neuroimaging dataset, demonstrating significant improvements in image quality.
    • Quantitative metrics including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and contrast-to-noise ratio (CNR) showed positive results.
    • Performance was further assessed using a novel no-reference metric for SR image quality.

    Conclusions:

    • The proposed self-supervised super-resolution (SSSR) technique shows promise for enhancing PET image quality and quantitation.
    • The method's ability to train without paired data ensures broader applicability in clinical research.
    • Simulation guidance was identified as a key factor contributing to the high performance of the SSSR technique.