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: Mar 24, 2026

Sample Drift Correction Following 4D Confocal Time-lapse Imaging
10:04

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

17.1K

Scatter correction for self-collimating SPECT using a 3D U-Net framework.

Yabo Zhao1,2, Wenyang Jiang1,2, Hai Hu1,2

  • 1Center for Advanced Quantum Studies, School of Physics and Astronomy, Beijing Normal University Beijing, China.

American Journal of Nuclear Medicine and Molecular Imaging
|March 23, 2026
PubMed
Summary

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

High-activity ⁹⁹Mo microresin fabrication for submillimeter SPECT system matrix acquisition.

Physics in medicine and biology·2026
Same author

SCT-Diff: Seamless Contextual Tracking via Diffusion Trajectory.

Journal of imaging·2026
Same author

A High-Performance Self-Collimation SPECT for Small Animal Imaging.

IEEE transactions on medical imaging·2026
Same author

Design optimization and simulated performance evaluation of a self-collimated cardiac SPECT with simultaneous high sensitivity and resolution.

Medical physics·2025
Same author

Regulation of PI3K signaling in cancer metabolism and PI3K-targeting therapy.

Translational breast cancer research : a journal focusing on translational research in breast cancer·2024
Same author

Butterfly-Inspired Multiple Cross-Linked Dopamine-Metal-Phenol Bioprosthetic Valves with Enhanced Endothelialization and Anticalcification.

ACS applied materials & interfaces·2024
Same journal

<sup>18</sup>F-Flurpiridaz PET in myocardial perfusion imaging: comparing effectiveness against traditional tracers.

American journal of nuclear medicine and molecular imaging·2026
Same journal

Positron emission tomography imaging of T-cell activity in cardiovascular disease and its emerging role in imaging adaptive immunity.

American journal of nuclear medicine and molecular imaging·2026
Same journal

Calibration and prediction of results after failed injection in SPECT renal dynamic imaging.

American journal of nuclear medicine and molecular imaging·2026
Same journal

Development and evaluation of a novel deuterated fluorine-18 PET tracer for MAO-B imaging.

American journal of nuclear medicine and molecular imaging·2026
Same journal

<sup>18</sup>F-NaF and <sup>18</sup>F-FDG PET/CT imaging of spinal instrumentation: case report and review of the literature.

American journal of nuclear medicine and molecular imaging·2026
Same journal

Bladder activity of different PSMA PET radioligands and impact of furosemide.

American journal of nuclear medicine and molecular imaging·2026
See all related articles
This summary is machine-generated.

A new 3D U-Net deep learning method accurately corrects scatter in self-collimating cardiac SPECT imaging. This advanced technique improves image quality and quantitative performance over traditional methods.

Area of Science:

  • Medical Imaging
  • Nuclear Medicine
  • Artificial Intelligence in Healthcare

Background:

  • Conventional single-photon emission computed tomography (SPECT) faces a resolution-sensitivity trade-off due to mechanical collimators.
  • Novel self-collimating SPECT systems enhance sensitivity but complicate scatter correction due to detector geometry.
  • Accurate scatter correction is crucial for quantitative analysis in advanced SPECT systems.

Purpose of the Study:

  • To develop and evaluate a 3D U-Net deep learning framework for direct scatter correction in novel self-collimating cardiac SPECT systems.
  • To compare the performance of the U-Net-based scatter correction method against conventional triple energy window (TEW) techniques.

Main Methods:

  • A 3D U-Net deep learning model was trained using GATE simulations of 36 XCAT phantoms to predict scatter-corrected images directly from uncorrected ones.
Keywords:
Deep learningSPECTU-Netscatter correctionself-collimation

More Related Videos

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.5K

Related Experiment Videos

Last Updated: Mar 24, 2026

Sample Drift Correction Following 4D Confocal Time-lapse Imaging
10:04

Sample Drift Correction Following 4D Confocal Time-lapse Imaging

Published on: April 12, 2014

17.1K
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
07:34

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.5K
  • The trained network was evaluated on high-contrast (H-Phantom) and low-contrast (L-Phantom) XCAT phantoms.
  • Performance was quantitatively assessed by comparing the U-Net approach with trapezoidal and triangular TEW methods.

    • Main Results:

    • The U-Net approach significantly outperformed TEW methods in both high- and low-contrast phantoms.
    • U-Net achieved superior contrast recovery coefficients, myocardium-to-blood-pool ratios, and contrast-to-noise ratios.
    • Images corrected using U-Net demonstrated higher structural similarity and lower normalized mean square error compared to TEW methods.

    Conclusions:

    • The proposed 3D U-Net-based scatter correction method offers more accurate scatter estimation for self-collimating SPECT systems.
    • This deep learning approach provides superior quantitative performance compared to conventional TEW methods.
    • The U-Net framework is a promising tool for enhancing image quality and diagnostic accuracy in advanced SPECT imaging.