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

Lung-Protective Ventilation Strategies for Relief from Ventilator-Associated Lung Injury in Patients Undergoing Craniotomy: A Bicenter Randomized, Parallel, and Controlled Trial.

Oxidative medicine and cellular longevity·2017
Same author

Electrochemical Oxidation of EDTA in Nuclear Wastewater Using Platinum Supported on Activated Carbon Fibers.

International journal of environmental research and public health·2017
Same author

Novel biomimetic enzyme for sensitive detection of superoxide anions.

Talanta·2017
Same author

The Expression of Formyl Peptide Receptor 1 is Correlated with Tumor Invasion of Human Colorectal Cancer.

Scientific reports·2017
Same author

An excited state underlies gene regulation of a transcriptional riboswitch.

Nature chemical biology·2017
Same author

(-)-Epigallocatechin-3-gallate attenuates myocardial injury induced by ischemia/reperfusion in diabetic rats and in H9c2 cells under hyperglycemic conditions.

International journal of molecular medicine·2017
Same journal

Co-assistant networks by pathology foundation model and convolutional neural network for gigapixel whole slide image analysis.

Medical image analysis·2026
Same journal

MBAS2024: A large-scale benchmark for multi-class bi-atrial segmentation in multi-center contrast-enhanced MRIs.

Medical image analysis·2026
Same journal

Respiratory motion augmentation for personalized super-resolution (RMApSR) of 3D cine MR images in MRI-guided radiotherapy.

Medical image analysis·2026
Same journal

Biom3d, a modular framework to host and develop 3D segmentation methods.

Medical image analysis·2026
Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026
Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026
See all related articles

Related Experiment Video

Updated: Jan 17, 2026

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

15.0K

Reinforced physiology-informed learning for image completion from partial-frame dynamic PET imaging.

Hengjia Ran1, Jianan Cui2, Xuhui Feng1

  • 1State Key Laboratory of Extreme Photonics and Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China.

Medical Image Analysis
|September 13, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel method to shorten dynamic positron emission tomography (PET) scans by using AI to reconstruct missing image frames. This technique improves accuracy and efficiency in dynamic PET imaging without requiring extensive training data.

Keywords:
Dynamic PETImplicit neural representationsKinetic modelParametric imagingPhysics informed neural networks

More Related Videos

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.8K
Functional Imaging with Reinforcement, Eyetracking, and Physiological Monitoring
08:47

Functional Imaging with Reinforcement, Eyetracking, and Physiological Monitoring

Published on: November 13, 2008

11.7K

Related Experiment Videos

Last Updated: Jan 17, 2026

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

15.0K
Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
14:21

Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking

Published on: August 6, 2013

18.8K
Functional Imaging with Reinforcement, Eyetracking, and Physiological Monitoring
08:47

Functional Imaging with Reinforcement, Eyetracking, and Physiological Monitoring

Published on: November 13, 2008

11.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Medicine

Background:

  • Dynamic positron emission tomography (PET) imaging with 18F-FDG is time-intensive, often exceeding an hour.
  • Reducing scan times is critical to minimize patient motion artifacts and enhance equipment throughput.
  • Shorter scan durations can compromise image quality and the accuracy of kinetic parameter estimation.

Purpose of the Study:

  • To develop and validate a method for completing missing frames in dynamic PET imaging.
  • To improve kinetic modeling and image reconstruction for accelerated PET scans.
  • To assess the performance of the proposed method against traditional techniques.

Main Methods:

  • A novel approach combining physiology-informed learning with time-implicit neural representations was developed.
  • Network training incorporated data, boundary, and physiology residual constraint terms based on a two-tissue compartment model.
  • The method was validated using simulated data, rat data, and human organ datasets from Biograph Vision Quadra.

Main Results:

  • The proposed method effectively reconstructs dynamic PET images and estimates kinetic parameters with reduced scan times.
  • Performance was evaluated across various scanning schemes, demonstrating feasibility with limited data and no need for specific training datasets.
  • The AI-driven method outperformed traditional nonlinear least squares (NLLS) fitting in reconstruction quality and computational efficiency.

Conclusions:

  • The developed physiology-informed neural network offers a promising solution for accelerating dynamic PET imaging.
  • This approach significantly enhances image reconstruction quality and parameter estimation accuracy.
  • The method achieves high performance metrics (e.g., SSIM > 0.98 in the brain, PSNR > 40 in the thorax), making it suitable for clinical applications.