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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

8.1K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
8.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Physics-inspired perspective on synergistic optimization: a deep receding-horizon optimization strategy for denitrification and ammonia slip suppression in waste incineration.

Bioresource technology·2026
Same author

Multidimensional Heteromorphic Bi<sub>2</sub>WO<sub>6</sub> Anchored With Au-Bi Bimetallic Nanodots Toward Photocatalytic Acetaldehyde Degradation.

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

Synthesis of alumina ceramic meta-fibers with tensile super-plasticity.

Nature communications·2026
Same author

Fly ash yield prediction-enabled optimization of municipal solid waste incineration: Reducing fly ash generation, disposal costs, and carbon emissions.

Waste management (New York, N.Y.)·2026
Same author

Mechanochemically induced interfacial electronic modulation in MnCe/BaTiO<sub>3</sub> for synergistic catalysis for NOx and o-dichlorobenzene.

Journal of colloid and interface science·2026
Same author

Probing contact electrification processes from interfacial charge transfer to bulk transport in semicrystalline polymers.

Nature communications·2026

Related Experiment Video

Updated: Sep 24, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.2K

Super-resolution reconstruction for parallel-beam SPECT based on deep learning and transfer learning: a preliminary

Zhibiao Cheng1, Junhai Wen1, Jun Zhang1

  • 1Department of Biomedical Engineering, School of Life Science, Beijing Institute of Technology, Beijing, China.

Annals of Translational Medicine
|May 9, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning network to enhance single-photon emission computed tomography (SPECT) imaging resolution using low-resolution detectors. The method successfully improved image quality and resolution, offering a cost-effective solution for disease diagnosis.

Keywords:
Parallel-beam single-photon emission computed tomography (SPECT)deep learningprojectionsuper-resolution (SR)transfer learning

More Related Videos

Preparation and Observation of Thick Biological Samples by Scanning Transmission Electron Tomography
08:04

Preparation and Observation of Thick Biological Samples by Scanning Transmission Electron Tomography

Published on: March 12, 2017

9.4K
Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.4K

Related Experiment Videos

Last Updated: Sep 24, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.2K
Preparation and Observation of Thick Biological Samples by Scanning Transmission Electron Tomography
08:04

Preparation and Observation of Thick Biological Samples by Scanning Transmission Electron Tomography

Published on: March 12, 2017

9.4K
Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Medicine

Background:

  • Single-photon emission computed tomography (SPECT) is crucial for diagnosing diseases like cancer and cardiovascular conditions.
  • High-resolution (HR) SPECT imaging demands costly HR projection data.
  • This research explores using deep learning to achieve HR SPECT images from low-resolution (LR) detectors.

Purpose of the Study:

  • To develop a super-resolution (SR) reconstruction network for parallel-beam SPECT.
  • To enable the generation of HR SPECT images from LR projection data.
  • To reduce the cost associated with obtaining high-resolution SPECT imaging.

Main Methods:

  • A deep learning and transfer learning-based SR reconstruction network was designed for parallel-beam SPECT.
  • Low-resolution (LR) SPECT sinograms were transformed into high-resolution (HR) sinograms.
  • The network was trained using digital phantoms and the XCAT phantom, with fine-tuning and accelerated training via transfer learning.

Main Results:

  • The proposed SR network demonstrated improved quantitative metrics (PSNR, SSIM) compared to benchmark methods.
  • Reconstructed images achieved resolutions comparable to those from HR projection data.
  • Validation was performed on simulation datasets with varying Poisson noise levels.

Conclusions:

  • A novel SR reconstruction network for parallel-beam SPECT was developed using deep learning and transfer learning.
  • The network shows potential for enhancing SPECT resolution in scanners with LR detectors.
  • This approach offers a viable method for improving diagnostic accuracy in SPECT imaging.