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

Corrigendum to "PET radiotracers targeting MDM2 protein interaction: From preclinical validation to first-in-human studies" [Pharmacol. Res. (2026) 230 108314].

Pharmacological research·2026
Same author

Hierarchical Semantic Concept Modeling for Generalizable Myocardial Pathology Segmentation on Multisequence CMR Images.

IEEE transactions on neural networks and learning systems·2026
Same author

PET radiotracers targeting MDM2 protein interaction: From preclinical validation to first-in-human studies.

Pharmacological research·2026
Same author

Differential response of soil microbial communities involved in N-cycling to short-term N input depends on the history of N application.

iScience·2026
Same author

DDRGK1-mediated UFMylation regulates DEHP-induced ER-phagy and ER-stress: Implication in the hippocampal neuronal apoptosis and cognitive deficits.

Journal of hazardous materials·2026
Same author

Alternative Splicing of TPM1 Mediated by SRPK3 Drives Cardiac Diastolic Dysfunction in Heart Failure With Preserved Ejection Fraction.

Circulation·2026
Same journal

It's PET but not as we know it: radiation protection considerations when using a novel specimen PET-CT scanner during tumour resections for urology and head & neck patients.

EJNMMI physics·2026
Same journal

Data-efficient unsupervised deep learning deformable SPECT/CT registration framework for voxel-level radionuclide therapy dosimetry: validation using clinical <sup>131</sup>I DTC therapy data.

EJNMMI physics·2026
Same journal

Impact of reduced <sup>18</sup>F-MK6240 PET/MR acquisition duration on image quality and tau pathology assessment in patients with cognitive impairment.

EJNMMI physics·2026
Same journal

Optimising [Formula: see text] PET imaging for dosimetry in SIRT: insights from phantom and simulation studies on the Discovery MI scanner.

EJNMMI physics·2026
Same journal

Denoising of 4D dynamic PET images using spatiotemporal regularization with integrated temporal restoration (SPRINTER).

EJNMMI physics·2026
Same journal

Limitations in diagnostics and quantification of small lesions with low uptake in the clinical context of prostate <sup>18</sup>F/<sup>68</sup>Ga-PSMA PET/MRI.

EJNMMI physics·2026
See all related articles

Related Experiment Video

Updated: Jan 9, 2026

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.9K

Neural network-aided unsupervised input function estimation for dual-time-window PET Patlak analysis.

Wenrui Shao1, Yarong Zhang2, Fen Du2

  • 1Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, 100871, China.

EJNMMI Physics
|December 8, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel neural network method for dual-time-window Patlak analysis, improving kinetic modeling accuracy without blood sampling. The approach enhances parametric imaging quality and reduces PET scan duration for lung cancer patients.

Keywords:
Dual-window acquisitionDynamic PETNeural networkPatlak plotUnsupervised learning

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.7K
Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG
09:35

Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG

Published on: March 10, 2017

9.6K

Related Experiment Videos

Last Updated: Jan 9, 2026

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials
12:03

A Method for Tracking the Time Evolution of Steady-State Evoked Potentials

Published on: May 25, 2019

8.9K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.7K
Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG
09:35

Automatic Detection of Highly Organized Theta Oscillations in the Murine EEG

Published on: March 10, 2017

9.6K

Area of Science:

  • Nuclear Medicine
  • Radiochemistry
  • Computational Biology

Background:

  • Dual-time-window (DTW) Patlak analysis is crucial for quantitative PET imaging, but traditional methods require invasive blood sampling and long scan durations.
  • Existing DTW and single-time-window methods can introduce bias and reduce comparability across patient cohorts.
  • Accurate estimation of the net influx constant (K_i) is essential for reliable quantitative analysis in oncology and neurology.

Purpose of the Study:

  • To develop and validate a novel dual-time-window (DTW) Patlak plot method using a neural network (NN) to eliminate invasive blood sampling and shorten scan times.
  • To improve the accuracy of net influx constant (K_i) estimation by addressing biases in traditional DTW methods.
  • To generate high-quality parametric imaging and reliable quantitative analysis within abbreviated scanning protocols.

Main Methods:

  • Developed an unsupervised, multi-branch neural network (NN) to estimate missing data intervals and generate pseudo input functions (IFs).
  • Constructed a weighted statistic (NNIF) from correlation scores between pseudo IFs and voxel-level data for accurate IF estimation.
  • Validated the NNIF approach using simulated data and [F-18]-FDG PET scans from 67 lung cancer patients, comparing it with other quantification techniques.

Main Results:

  • The NNIF method achieved high accuracy in IF estimation (max MAD of 0.04 in patient studies) and consistent K_i regression across DTW protocols.
  • Simulation studies showed a best relative absolute error (RAE) of 0.0302.
  • Clinical validation demonstrated optimal average PSNR of 97.40 dB and R-squared of 0.991 for parametric imaging and ROI-based analysis, respectively.

Conclusions:

  • A weighted statistic derived from a multi-branch neural network can accurately estimate the complete input function (IF).
  • This approach enables high-quality parametric imaging with significantly reduced scanning times.
  • The method ensures accurate Patlak analysis, offering a more efficient and reliable quantitative PET imaging solution.