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

Validation of a knowledge-based boundary detection algorithm: a multicenter study

M W Groch1, W D Erwin, P H Murphy

  • 1Northwestern University School of Medicine, Chicago, Ill., USA.

European Journal of Nuclear Medicine
|June 1, 1996
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

Do patients with low volume prostate cancer have prostate specific antigen recurrence following radical prostatectomy?

Journal of clinical pathology·2008
Same author

Seasonal variation of reproductive performance, foetal development and progesterone concentrations of sheep in the subtropics.

Reproduction in domestic animals = Zuchthygiene·2008
Same author

Validation of a soccer skill test for use with females.

International journal of sports medicine·2008
Same author

Assessment of the need to coat particle collection cups of the NGI to mitigate droplet bounce when evaluating nebuliser-produced droplets.

Pharmeuropa scientific notes·2008
Same author

Cooling the NGI - an approach to size a nebulised aerosol more accurately.

Pharmeuropa scientific notes·2008
Same author

Multiplex PCR for differential diagnosis of emerging typhoidal pathogens directly from blood samples.

Epidemiology and infection·2008
Same journal

[Not Available].

European journal of nuclear medicine·2016
Same journal

A Window on Latin America.

European journal of nuclear medicine·2016
Same journal

Erratum: Eur J Nucl Med (1999) 26: 686-692.

European journal of nuclear medicine·2016
Same journal

Nuclear medicine in the next decade.

European journal of nuclear medicine·2014
Same journal

Erratum: Impact of attenuation correction on the accuracy of FDG-PET in patients with abdominal tumors: a free-response ROC analysis.

European journal of nuclear medicine·2014
Same journal

(99m)Tc(V)DMSA quantitatively predicts (188)Re(V)DMSA distribution in patients with prostate cancer metastatic to bone.

European journal of nuclear medicine·2014
See all related articles

A novel operator-independent algorithm accurately detects cardiac boundaries in multigated blood pool studies. This artificial intelligence-driven tool shows high success and correlation with standard ejection fraction calculations.

Area of Science:

  • Cardiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Multigated blood pool (MGBP) studies are crucial for assessing cardiac function.
  • Accurate boundary detection of cardiac chambers, particularly the left ventricle (LV), is essential for reliable ejection fraction (LVEF) calculation.
  • Current methods often rely on operator-dependent boundary detection, introducing variability.

Purpose of the Study:

  • To evaluate a completely operator-independent boundary detection algorithm, the knowledge-based boundary detector (KBBD), for MGBP studies.
  • To assess the performance of the KBBD algorithm across different imaging geometries (conventional and zoomed/tilted).
  • To compare LVEF calculations derived from KBBD with standard institutional methods.

Main Methods:

Related Experiment Videos

  • The knowledge-based boundary detector (KBBD) algorithm utilizes rule sets for cardiac chamber and feature localization.
  • The nondeterministic algorithm employs multiple processing pathways adaptable to conventional (CONV) and zoomed/tilted (ZOOM) imaging.
  • A total of 253 MGBP cases (157 CONV, 96 ZOOM) were analyzed across four medical centers, comparing KBBD-derived LVEF with standard calculations.

    • Main Results:

    • The KBBD algorithm achieved an overall success rate of 99.2% in defining LV boundaries.
    • A high overall correlation coefficient (r=0.95, P<0.001) was observed between KBBD LVEFs and standard calculations.
    • Individual success rates were 98% (r=0.93) for CONV and 100% (r=0.95) for ZOOM geometries.

    Conclusions:

    • The operator-independent KBBD algorithm demonstrates high accuracy and reliability for boundary detection in MGBP studies.
    • The algorithm is adaptable to various clinical imaging situations, including complex geometries.
    • KBBD offers automated processing with performance comparable to experienced human operators, enhancing efficiency and consistency.