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: Oct 1, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

3D Segmentation Guided Style-Based Generative Adversarial Networks for PET Synthesis.

Yang Zhou, Zhiwen Yang, Hui Zhang

    IEEE Transactions on Medical Imaging
    |March 3, 2022
    PubMed
    Summary
    This summary is machine-generated.

    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

    Weakly supervised histopathology image segmentation with self-attention.

    Medical image analysis·2023
    Same author

    Integrated 3d flow-based multi-atlas brain structure segmentation.

    PloS one·2022
    Same author

    Whole brain segmentation with full volume neural network.

    Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2021
    Same author

    Deep learning in digital pathology image analysis: a survey.

    Frontiers of medicine·2020
    Same author

    ANHIR: Automatic Non-Rigid Histological Image Registration Challenge.

    IEEE transactions on medical imaging·2020
    Same author

    MRI Cross-Modality Image-to-Image Translation.

    Scientific reports·2020

    This study introduces a novel method to enhance low-dose positron emission tomography (PET) images to full-dose quality. The segmentation-guided style-based generative adversarial network (SGSGAN) improves image synthesis, especially in critical regions.

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Radiology

    Background:

    • Positron emission tomography (PET) imaging involves radioactive hazards with full-dose scans.
    • Low-dose PET images often lack sufficient quality for clinical applications.
    • Translating low-dose PET to full-dose quality is highly desirable for safer imaging.

    Purpose of the Study:

    • To develop an advanced deep learning framework for synthesizing high-quality, full-dose PET images from low-dose inputs.
    • To address limitations of previous methods by incorporating feature weighting and region-specific synthesis.
    • To improve the clinical utility of PET imaging by reducing radiation exposure.

    Main Methods:

    • Proposed a novel segmentation-guided style-based generative adversarial network (SGSGAN).

    More Related Videos

    Computer-Generated Animal Model Stimuli
    26:43

    Computer-Generated Animal Model Stimuli

    Published on: July 29, 2007

    11.1K
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.2K

    Related Experiment Videos

    Last Updated: Oct 1, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    538
    Computer-Generated Animal Model Stimuli
    26:43

    Computer-Generated Animal Model Stimuli

    Published on: July 29, 2007

    11.1K
    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
    12:06

    Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

    Published on: March 3, 2023

    4.2K
  • Employed a style-based generator with style modulation for realistic texture synthesis.
  • Integrated a task-driven strategy coupling segmentation with a generative adversarial network (GAN) framework.

    • Main Results:

    • The SGSGAN framework demonstrated superior performance in PET image synthesis compared to existing methods.
    • The style-based generator effectively controlled hierarchical features for enhanced image realism.
    • The coupled segmentation task improved translation performance, particularly in regions of interest.

    Conclusions:

    • The SGSGAN offers a significant advancement in low-dose to full-dose PET image translation.
    • This method enhances image quality and preserves crucial details in critical regions.
    • SGSGAN has the potential to enable safer and more effective PET imaging practices.