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

Transient Ischemic Dilation with <sup>18</sup>F-flurpiridaz PET: Establishing Thresholds for a Novel Radiotracer.

Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology·2026
Same author

Automated AI-Based Aortic Measurements From Attenuation Correction CT as an Adjunctive Cardiovascular Risk Biomarker: An International Multicenter Study.

Circulation. Cardiovascular imaging·2026
Same author

Machine Learning Multiorgan Analysis of Coronary CT Angiography Body Composition, Myocardial Infarction, and Mortality in the SCOT-HEART Trial.

Radiology·2026
Same author

Stereoretentive Nucleophilic Aromatic Substitution Accesses Atropisomeric 4-Amino-N-Arylquinolinium Salts.

Chemistry (Weinheim an der Bergstrasse, Germany)·2026
Same author

Revisiting Perfusion in the Forgotten Right Ventricle: Artificial Intelligence-Enhanced Quantification on PET/CT.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

Incremental Prognostic Value of Subendocardial Myocardial Flow Reserve in Patients With Normal Perfusion.

Circulation·2026

Related Experiment Video

Updated: Sep 16, 2025

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

18.4K

Dynamic frame-by-frame motion correction for 18F-flurpiridaz PET-MPI using convolution neural network.

Meghana Urs1, Aditya Killekar1, Valerie Builoff1

  • 1Department of Medicine (Division of Artificial Intelligence in Medicine), Cedars-Sinai Medical Center, Los Angeles, CA.

Medrxiv : the Preprint Server for Health Sciences
|July 9, 2025
PubMed
Summary

A new deep learning (DL) framework automates motion correction for 18F-flurpiridaz PET imaging, improving myocardial blood flow (MBF) and flow reserve (MFR) quantification. This AI approach is faster and as accurate as manual methods.

Keywords:
18F-flurpiridazPETdeep learningmotion correctionmyocardial blood flowmyocardial flow reserve

More Related Videos

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

1.1K

Related Experiment Videos

Last Updated: Sep 16, 2025

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

18.4K
Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K
Profiling Maternal Behavior Responses During Whole-Brain Imaging
07:12

Profiling Maternal Behavior Responses During Whole-Brain Imaging

Published on: January 24, 2025

1.1K

Area of Science:

  • Nuclear Medicine
  • Cardiovascular Imaging
  • Artificial Intelligence in Medical Imaging

Background:

  • Precise quantification of myocardial blood flow (MBF) and myocardial flow reserve (MFR) using 18F-flurpiridaz PET is crucial for diagnosing coronary artery disease (CAD).
  • Accurate MBF and MFR measurements heavily depend on effective motion correction (MC) of PET data.
  • Current manual frame-by-frame MC methods are time-consuming, require extensive expertise, and introduce significant inter-observer variability.

Purpose of the Study:

  • To develop and validate a deep learning (DL) framework for automated motion correction (MC) in 18F-flurpiridaz PET imaging.
  • To compare the diagnostic performance and quantitative accuracy of the DL-based MC method against manual MC and standard non-AI automatic MC techniques.

Main Methods:

  • A 3D ResNet architecture was utilized to process 3D PET volumes and generate motion vectors for automated MC.
  • The DL framework was trained and validated using data from 32 sites of a Phase III clinical trial (NCT01347710), with manual corrections by two experienced operators serving as ground truth.
  • Data augmentation with simulated motion vectors was employed to enhance the robustness of the DL model, which was compared against manual and standard non-AI automatic MC methods.

Main Results:

  • The deep learning-based motion correction (DL-MC) for MBF and MFR demonstrated diagnostic accuracy comparable to manual MC in detecting significant CAD (AUCs ranging from 0.889 to 0.897 vs. 0.877 for standard non-AI MC, and significantly higher than No-MC at 0.835).
  • Quantitative analysis showed excellent agreement between DL-MC and manual MC for both MBF (95% confidence limits ±0.24ml/g/min) and MFR (95% confidence limits ±0.49ml/g/min).
  • The DL-MC method was significantly faster than manual correction while maintaining diagnostic comparability.

Conclusions:

  • The proposed DL-MC framework provides a fast and automated solution for motion correction in 18F-flurpiridaz PET-MPI.
  • DL-MC achieves diagnostic accuracy and quantitative agreement with manual MC, offering a reliable alternative to manual and standard non-AI automatic methods.
  • This automated approach has the potential to improve the efficiency and consistency of MBF and MFR quantification in clinical practice.