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

Identification of anthropometric variables influencing the prediction of manual strength using advanced models to prevent occupational injuries in the economically active population.

Work (Reading, Mass.)·2025
Same author

Comparison of machine learning and deep learning models in manual strength prediction using anthropometric variables.

International journal of occupational safety and ergonomics : JOSE·2025
Same author

Sex classification from hand X-ray images in pediatric patients: How zero-shot Segment Anything Model (SAM) can improve medical image analysis.

Computers in biology and medicine·2025
Same author

Adaptive filter with Riemannian manifold constraint.

Scientific reports·2023
Same author

A Weighted and Distributed Algorithm for Range-Based Multi-Hop Localization Using a Newton Method.

Sensors (Basel, Switzerland)·2021
Same author

Gait Biomarkers Classification by Combining Assembled Algorithms and Deep Learning: Results of a Local Study.

Computational and mathematical methods in medicine·2020

Related Experiment Video

Updated: Nov 27, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

488

Reconstruction of PET Images Using Cross-Entropy and Field of Experts.

Jose Mejia1, Alberto Ochoa2, Boris Mederos3

  • 1Department of Electrical and Computation Engineering, Universidad Autónoma de Ciudad Juárez, Ciudad Juárez 32310, Mexico.

Entropy (Basel, Switzerland)
|December 3, 2020
PubMed
Summary

This study introduces a novel Field of Experts (FoE) model to enhance Positron Emission Tomography (PET) image reconstruction. The FoE model improves image accuracy, particularly in low count rate scenarios, by incorporating prior anatomical information.

Keywords:
field of expertspositron emission tomographyreconstruction

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.7K

Related Experiment Videos

Last Updated: Nov 27, 2025

Photorealistic Learned Landscapes for Augmented Reality
06:54

Photorealistic Learned Landscapes for Augmented Reality

Published on: June 27, 2025

488
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.7K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.7K

Area of Science:

  • Medical Imaging
  • Image Reconstruction
  • Computational Science

Background:

  • Positron Emission Tomography (PET) data reconstruction is challenging, especially at low count rates.
  • Poisson noise significantly impacts statistical uncertainty in PET measurements.
  • Prior information is often used to enhance PET image quality.

Purpose of the Study:

  • To develop a novel method for improving PET image reconstruction at low count rates.
  • To address noise and low count data issues in PET imaging.
  • To leverage a Field of Experts (FoE) model for anatomical spatial dependency modeling.

Main Methods:

  • Proposed a modified Maximum Expectation (MXE) algorithm for PET image reconstruction.
  • Incorporated a Field of Experts (FoE) model as a regularizing term in the objective function.
  • Utilized cross-entropy as a fidelity term within the modified MXE algorithm.

Main Results:

  • The proposed FoE-based method demonstrated accurate PET image estimation.
  • The method showed superior performance compared to Expectation Maximization (EM) and relative difference prior methods.
  • Significant improvements were observed in low count rate PET acquisitions.

Conclusions:

  • The Field of Experts model effectively captures anatomical priors for PET reconstruction.
  • The modified MXE algorithm with FoE regularization enhances image quality and accuracy in low-count PET data.
  • This approach offers a promising solution for challenging PET imaging conditions.