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

Computed Tomography01:10

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by
Same author

Renal Complement C3 Deposition is Associated with Glomerular Prothrombotic Milieu in Patients with IgA Nephropathy.

Journal of inflammation research·2026
Same author

Chronic kidney disease in women: Global trends and metabolic-cardiovascular associations.

Chinese medical journal·2026
Same author

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
Same author

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026
Same author

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution.

Advances in neural information processing systems·2026
Same author

Mitochondrial quality control in health and disease: Updates 2026.

Chinese medical journal·2026

Related Experiment Video

Updated: Jun 23, 2026

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.6K

Cycle-consistent learning-based hybrid iterative reconstruction for whole-body PET imaging.

Bao Yang1, Long Zhou2, Ling Chen1

  • 1Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, People's Republic of China.

Physics in Medicine and Biology
|March 9, 2022
PubMed
Summary

This study introduces a new hybrid iterative reconstruction method for whole-body PET imaging, achieving high image resolution and accurate tumor quantification with fast processing times.

Keywords:
cycle-consistent learninghybrid iterative reconstructionnoise reductionpositron emission tomographytumor quantification

More Related Videos

Whole-body PET/MRI of Pediatric Patients: The Details That Matter
10:02

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

14.8K
Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis
07:45

Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis

Published on: October 25, 2024

506

Related Experiment Videos

Last Updated: Jun 23, 2026

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
10:48

PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

Published on: December 28, 2017

9.6K
Whole-body PET/MRI of Pediatric Patients: The Details That Matter
10:02

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

14.8K
Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis
07:45

Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis

Published on: October 25, 2024

506

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Nuclear Medicine

Background:

  • Iterative reconstruction (IR) offers superior image quality in Positron Emission Tomography (PET) but is computationally intensive.
  • Analytic reconstruction methods are faster but provide lower image resolution and quantification accuracy.
  • Existing deep learning methods for PET reconstruction often require extensive training data or post-processing.

Purpose of the Study:

  • To develop a novel cycle-consistent learning-based hybrid iterative reconstruction (IR) method for whole-body PET imaging.
  • To achieve image resolution and tumor quantification comparable to traditional IR, with processing times close to analytic reconstruction.
  • To improve the accuracy and efficiency of PET image reconstruction for clinical applications.

Main Methods:

  • A cycle-consistent learning framework was developed, unrolling a reconstruction mapping into a neural network with stacked convolutional layers.
  • The method trains reconstruction and inverse mappings simultaneously by minimizing cycle-consistent loss, starting from backprojected PET data.
  • The approach approximates deblurring filters accounting for the point spread function and PET system physics.

Main Results:

  • Phantom studies showed low relative error (4.0% ± 0.7%) in mean activity, comparable to full-count IR.
  • The method achieved significant noise reduction (48.1% ± 0.5%) compared to low-count IR, outperforming CycleGAN in resolution and contrast.
  • Patient studies demonstrated substantial noise reduction (44.6% ± 8.0%) in lung and liver, while preserving regional mean activity and halving reconstruction time compared to conventional IR.

Conclusions:

  • Cycle-consistent learning from backprojection offers an efficient and accurate alternative for whole-body PET image reconstruction.
  • The method improves reconstruction accuracy, reduces memory demands, and offers fast implementation speeds for clinical use.
  • This approach bridges the gap between the speed of analytic reconstruction and the quality of iterative reconstruction in PET imaging.