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

An artificial neural net and error backpropagation to reconstruct single photon emission computerized tomography

P Knoll1, S Mirzaei, A Müllner

  • 1L. Boltzmann Institute of Nuclear Medicine, Vienna, Austria.

Medical Physics
|March 17, 1999
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

Search for scalar diphoton resonances in the mass range 65-600 GeV with the ATLAS detector in pp collision data at √s=8 TeV.

Physical review letters·2014
Same author

Evidence for electroweak production of W±W±jj in pp collisions at sqrt[s] = 8 TeV with the ATLAS detector.

Physical review letters·2014
Same author

[Turnover of Non-medical Staff in Outpatient Oncology Practices: Is Building Social Capital a Solution?].

Gesundheitswesen (Bundesverband der Arzte des Offentlichen Gesundheitsdienstes (Germany))·2014
Same author

FAT1 expression and mutations in adult acute lymphoblastic leukemia.

Blood cancer journal·2014
Same author

Measurements of four-lepton production at the Z resonance in pp collisions at sqrt[s] = 7 and 8 TeV with ATLAS.

Physical review letters·2014
Same author

Can a stressed oncologist be good in a consultation? A qualitative study on the oncologists' perception.

European journal of cancer care·2014

This study introduces a novel artificial neural network algorithm for single photon emission computerized tomography (SPECT) image reconstruction. The new method enhances image quality compared to traditional filtered backprojection, offering faster processing for nuclear medicine applications.

Area of Science:

  • Nuclear Medicine
  • Medical Imaging
  • Artificial Intelligence in Healthcare

Background:

  • Current single photon emission computerized tomography (SPECT) data reconstruction relies on filtered backprojection or iterative methods.
  • These established algorithms have limitations in image quality and processing time.

Purpose of the Study:

  • To introduce and evaluate a novel artificial neural network (ANN) algorithm for SPECT transaxial slice reconstruction.
  • To compare the performance of the ANN algorithm against traditional filtered backprojection in terms of image quality and reconstruction speed.

Main Methods:

  • Development and implementation of an artificial neural network (multilayer perception) with error backpropagation for SPECT data reconstruction.
  • Validation using a mathematical model and testing on heart and Jaszczak phantoms.

Related Experiment Videos

  • Clinical evaluation with (111)In octreotide SPECT and (99m)Tc MDP bone SPECT data.

    • Main Results:

    • The ANN algorithm achieved a reconstruction time of approximately 45 seconds per transaxial slice for a 64x64 matrix.
    • Phantom studies demonstrated comparable or improved image quality over filtered backprojection.
    • Initial clinical results indicate enhanced image quality in SPECT scans using the ANN approach.

    Conclusions:

    • Artificial neural networks offer a promising alternative for SPECT image reconstruction.
    • The developed ANN algorithm provides an effective method for improving SPECT image quality and potentially reducing reconstruction times.
    • This AI-driven approach shows potential for routine digital image processing in nuclear medicine departments.