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: Nov 28, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

351

Denoising non-steady state dynamic PET data using a feed-forward neural network.

G I Angelis1,2, O K Fuller1,3, J E Gillam4

  • 1Imaging Physics Laboratory, Brain and Mind Centre, Camperdown, NSW 2050, Australia.

Physics in Medicine and Biology
|November 25, 2020
PubMed
Summary
This summary is machine-generated.

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

Robustness of post-reconstruction and direct kinetic parameter estimates under rigid head motion in dynamic brain PET imaging.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2018
Same author

Rigid motion correction of dual opposed planar projections in single photon imaging.

Physics in medicine and biology·2017
Same author

Polarisation-based coincidence event discrimination: an in silico study towards a feasible scheme for Compton-PET.

Physics in medicine and biology·2016
Same author

Noise evaluation of Compton camera imaging for proton therapy.

Physics in medicine and biology·2015
Same author

Towards optimal imaging with PET: an in silico feasibility study.

Physics in medicine and biology·2014
Same author

Application of adaptive kinetic modelling for bias propagation reduction in direct 4D image reconstruction.

Physics in medicine and biology·2014
Same journal

Deep learning-based dose prediction to enhance planning efficiency in cervical brachytherapy with hybrid applicators.

Physics in medicine and biology·2026
Same journal

Corrigendum: Referenceless MR thermometry-a comparison of five methods (2017<i>Phys. Med. Biol</i>.<b>62</b>1-16).

Physics in medicine and biology·2026
Same journal

Corrigendum: Measured and Monte Carlo simulated electron backscatter to the monitor chamber for the varian TrueBeam linac (2016<i>Phys. Med. Biol</i>.<b>61</b>8779).

Physics in medicine and biology·2026
Same journal

Corrigendum: 3D range-modulator for scanned particle therapy: development, Monte Carlo simulations and experimental evaluation (2017<i>Phys. Med. Biol</i>.<b>62</b>7075).

Physics in medicine and biology·2026
Same journal

Recent progress in applications of computing to radiotherapy (ICCR 2016).

Physics in medicine and biology·2026
Same journal

Novel TMS coils designed using an inverse boundary element method.

Physics in medicine and biology·2026
See all related articles

A novel artificial neural network effectively denoises dynamic PET images, preserving crucial activation signals. This method improves signal-to-noise ratio and enhances the accuracy of pharmacokinetic parameter estimation in neurotransmitter studies.

Area of Science:

  • Medical Imaging
  • Neuroscience
  • Artificial Intelligence

Background:

  • Dynamic Positron Emission Tomography (PET) imaging is vital for studying neurotransmitter dynamics but suffers from noise, compromising image quality and parameter reliability.
  • Existing denoising methods often reduce spatio-temporal variability but can erase critical temporal signatures of transient activation responses in non-steady-state studies.

Purpose of the Study:

  • To develop and evaluate an artificial neural network for temporal denoising of dynamic PET images, specifically designed to preserve transient neurotransmitter activation responses.
  • To compare the performance of this neural network against the widely used Highly Constrained Back Projection (HYPR) filter in dynamic [11C]raclopride activation studies.

Main Methods:

  • A feed-forward perceptron neural network was trained to identify time-activity curve temporal profiles while preserving activation signals.

More Related Videos

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

Related Experiment Videos

Last Updated: Nov 28, 2025

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

351
Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K
  • The neural network's denoising capabilities were assessed using simulated Geant4 data of a rat brain phantom and experimental data from freely moving animals.
  • Performance was evaluated based on signal-to-noise ratio improvement, preservation of temporal signatures, and accuracy of pharmacokinetic parameter estimation using the lp-ntPET model.

    • Main Results:

    • The neural network demonstrated efficient improvement in the noise characteristics of dynamic PET data in the temporal domain.
    • It led to more reliable voxel-wise estimation of activation responses in target regions compared to the HYPR filter.
    • Denoising with the neural network resulted in improved accuracy and precision of estimated model parameters, outperforming the HYPR filter in temporal denoising.

    Conclusions:

    • The proposed artificial neural network offers a superior approach to temporal denoising in non-steady-state dynamic PET studies, effectively preserving activation responses.
    • This method enhances the reliability of pharmacokinetic parameter estimation and improves the accuracy of neurotransmitter activation studies.
    • The neural network's effectiveness is particularly notable in noisy dynamic PET data, offering significant advantages over traditional filtering techniques.