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 Videos

Neural network-based PET image reconstruction

Y Kosugi1, M Sase, Y Suganami

  • 1Tokyo Institute of Technology, Yokohama, Japan. kosugi@pms.titech.ac.jp

Methods of Information in Medicine
|February 21, 1998
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

Japanese species of <i>Alternaria</i> and their species boundaries based on host range.

Fungal systematics and evolution·2020
Same author

Sézary syndrome involving the intestinal tract.

Clinical and experimental dermatology·2019
Same author

Marine radioecology after the Fukushima Dai-ichi nuclear accident: Are we better positioned to understand the impact of radionuclides in marine ecosystems?

The Science of the total environment·2017
Same author

Seasonal variations of zooplankton biomass and size-fractionated abundance in relation to environmental changes in a tropical mangrove estuary in the Straits of Malacca.

Journal of environmental biology·2017
Same author

An analysis of nonlinear dynamics underlying neural activity related to auditory induction in the rat auditory cortex.

Neuroscience·2016
Same author

Tunic morphology and cellulosic components of pyrosomas, doliolids, and salps (thaliacea, urochordata).

The Biological bulletin·2015
Same journal

Design and methodological development of a digital clinical safety training programme informed by a national framework: a New Zealand case study.

Methods of information in medicine·2026
Same journal

Panic Prediction from Digital Phenotyping: Subject-Level Cross-Validation Reveals Limited Between-Person Generalization.

Methods of information in medicine·2026
Same journal

Agent-Based Modeling Approach for Population Dynamics of the Biological Vector Aedes Aegypti.

Methods of information in medicine·2026
Same journal

A Statistical Framework for Person-centered Analysis of Digital Service Use in Public Health and Social Care.

Methods of information in medicine·2026
Same journal

Assessing the Quality of Electronic Discharge Summaries: A Cross-Sectional Study Using the Validated Spanish Version of the PDQI-9.

Methods of information in medicine·2026
Same journal

A Knowledge Graph-Driven Hypergeometric Efficacy Prediction Model for Classical Traditional Chinese Herbal Formulas.

Methods of information in medicine·2026
See all related articles

This study introduces an MR-embedded neural network to improve Positron Emission Tomography (PET) image analysis. The model reduces partial volume effects for more precise brain function studies.

Area of Science:

  • Neuroimaging
  • Medical Physics
  • Computational Neuroscience

Background:

  • Positron Emission Tomography (PET) imaging is crucial for studying localized brain function.
  • Conventional deconvolution methods in PET analysis have limitations in providing precise functional information.
  • Partial volume effects can degrade the accuracy of quantitative PET studies.

Purpose of the Study:

  • To develop an advanced model for PET image analysis that overcomes limitations of conventional deconvolution.
  • To incorporate prior knowledge from Magnetic Resonance (MR) images into PET analysis.
  • To reduce partial volume effects for enhanced accuracy in blood flow profile restoration.

Main Methods:

  • An MR-embedded neural network model was designed and implemented.

Related Experiment Videos

  • The model integrates tissue distribution information from MR images.
  • A priori knowledge, including smoothness constraints, was incorporated into the deconvolution process.

    • Main Results:

    • The proposed model effectively reduces partial volume effects in PET image analysis.
    • Restoration of blood flow profiles from PET images is significantly improved.
    • Enhanced precision in studying localized brain function is achieved.

    Conclusions:

    • The MR-embedded neural network offers a superior approach to PET image analysis compared to conventional deconvolution.
    • Integrating MR data and prior knowledge enhances the accuracy of quantitative PET studies.
    • This method holds promise for more precise investigations of brain function.