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: Jun 11, 2025

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

11.7K

Deep learned triple-tracer multiplexed PET myocardial image separation.

Bolin Pan1, Paul K Marsden1, Andrew J Reader1

  • 1School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.

Frontiers in Nuclear Medicine
|October 9, 2024
PubMed
Summary

A new deep learning method effectively separates signals from triple-tracer positron emission tomography (PET) scans without needing arterial input functions. This approach reduces noise and improves accuracy compared to conventional methods for multiplexed PET imaging.

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

Generative Consistency Models for Estimation of Kinetic Parametric Image Posteriors in Total-Body PET.

IEEE transactions on medical imaging·2026
Same author

Diffusion models for medical image reconstruction.

BJR artificial intelligence·2026
Same author

Targeting TPX2-dependent lineage plasticity by CDK4/6 inhibition reverses therapy resistance in neuroendocrine bladder carcinoma.

Cell reports. Medicine·2026
Same author

Miniature and versatile genome regulation TnpB-ωRNA toolkits facilitate cancer immunotherapy.

Nature communications·2026
Same author

Personalized MR-Informed Diffusion Models for 3D PET Image Reconstruction.

IEEE transactions on radiation and plasma medical sciences·2025
Same author

Reprogramming the tumor microenvironment with c-MYC-based gene circuit platform to enhance specific cancer immunotherapy.

Nature communications·2025

Area of Science:

  • Medical Imaging
  • Nuclear Medicine
  • Artificial Intelligence

Background:

  • Multiplexed positron emission tomography (mPET) allows simultaneous acquisition of physiological and pathological data from multiple radiotracers in a single scan.
  • Signal separation in mPET is challenging because the scanner measures the combined signals of all tracers.
  • Conventional multi-tracer compartment modeling (MTCM) requires staggered injections and known arterial input functions (AIFs).

Purpose of the Study:

  • To develop and evaluate a deep learning-based method for separating signals from triple-tracer PET images without requiring AIFs.
  • To assess the performance of the proposed method in reducing noise and improving accuracy in myocardial imaging.

Main Methods:

  • A deep learning framework was designed to separate triple-tracer PET images.
Keywords:
compartmental modelingdata-driven learningdeep learningimage separationmultiplexed positron emission tomography

More Related Videos

3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

8.7K
High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

3.6K

Related Experiment Videos

Last Updated: Jun 11, 2025

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

11.7K
3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

8.7K
High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals
11:09

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

3.6K
  • The network input consisted of dynamic triple-tracer noisy MLEM reconstructions.
  • Dynamic single-tracer noisy MLEM reconstructions served as training labels.

    • Main Results:

    • The proposed deep learning method significantly reduced noise in separated single-tracer images compared to standard single-tracer imaging.
    • It demonstrated lower bias and standard deviation at both voxel and region of interest (ROI) levels compared to the MTCM-based method.
    • The method effectively utilizes spatiotemporal information for improved separation.

    Conclusions:

    • The deep learning-based method offers superior performance for triple-tracer PET signal separation compared to conventional MTCM.
    • The approach shows significant potential for application in pre-clinical and clinical multiplexed PET studies.
    • This method advances the field of quantitative analysis in dynamic multi-tracer PET imaging.