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

Segmented attenuation correction using artificial neural networks in positron tomography

S K Yu1, C Nahmias

  • 1Department of Nuclear Medicine, McMaster University Medical Center, Hamilton, Ontario, Canada.

Physics in Medicine and Biology
|October 1, 1996
PubMed
Summary

This study introduces an artificial neural network-based segmented attenuation correction technique for cardiac positron emission tomography. The novel method accurately corrects for attenuation and scatter, improving image quality and reducing scan times.

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

[Experience summary of coagulation rebalancing therapy for heat stroke-induced coagulopathy].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2025
Same author

Comparison of modeling accuracy between Radixact<sup>®</sup>and CyberKnife<sup>®</sup>Synchrony<sup>®</sup>respiratory tracking system.

Biomedical physics & engineering express·2021
Same author

Initial clinical experience of patient-specific QA of treatment delivery in online adaptive radiotherapy using a 1.5 T MR-Linac.

Biomedical physics & engineering express·2021
Same author

Correction to: Molecular characterization of Blastocystis sp. in captive wild animals in Qinling Mountains.

Parasitology research·2017
Same author

Molecular characterization of Blastocystis sp. in captive wild animals in Qinling Mountains.

Parasitology research·2017
Same author

Filmless methods for quality assurance of Tomotherapy using ArcCHECK.

Medical physics·2017

Area of Science:

  • Medical Imaging
  • Nuclear Medicine
  • Artificial Intelligence

Background:

  • Measured attenuation correction in cardiac positron emission tomography (PET) is limited by insufficient counting statistics and scatter radiation.
  • These limitations lead to underestimation of attenuation coefficients, impacting image accuracy.

Purpose of the Study:

  • To develop and validate a novel segmented attenuation correction technique using artificial neural networks (ANNs) for cardiac PET.
  • To improve the accuracy and reproducibility of attenuation coefficient measurements and activity concentration recovery.

Main Methods:

  • Development of a segmented attenuation correction technique employing ANNs.
  • Validation using phantom studies and verification in human subjects.
  • Assessment of accuracy, reproducibility, and sensitivity to scatter contamination.

Related Experiment Videos

Main Results:

  • The ANN-based segmented technique provides accurate and reproducible attenuation coefficients.
  • Accurate recovery of activity concentrations in reconstructed emission images was achieved.
  • The method is subject-independent and robust against scatter contamination in transmission data.

Conclusions:

  • The developed segmented attenuation correction technique offers significant improvements for cardiac PET imaging.
  • It allows for reduced transmission scan times while maintaining high accuracy.
  • The technique accurately predicts attenuation coefficients across a wide range, with or without scatter correction.