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

Structural and statistical object recognition in medical images.

C Dary1, Y Bizais, T Arnoult

  • 1Projet DIMI, HGRL CHRN, Nantes, France.

Progress in Clinical and Biological Research
|January 1, 1991
PubMed
Summary

Utilizing boundary objects (BOS) nearly doubles the success rate for left ventricular (LV) identification, achieving 90% accuracy. Errors, including undetected or misclassified LVs, are minimized through improved techniques and updated models.

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

A multiresolution image based approach for correction of partial volume effects in emission tomography.

Physics in medicine and biology·2006
Same author

Validation of a Monte Carlo simulation of the Philips Allegro/GEMINI PET systems using GATE.

Physics in medicine and biology·2006
Same author

FDG PET in epithelioid hemangioendothelioma.

Clinical nuclear medicine·2004
Same author

Technology related parameters affecting quantification in positron emission tomography imaging.

Nuclear medicine communications·2004
Same author

Predicting pesticide emissions and downwind concentrations using correlations with estimated vapor pressures.

Journal of agricultural and food chemistry·2001
Same author

Post-synchronized scintigraphic data to estimate antral motility.

Nuclear medicine communications·2001

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Cardiology

Background:

  • Accurate left ventricular (LV) identification is crucial for cardiac diagnosis.
  • Current methods face challenges with atypical image presentations and novel boundary objects (BOS).

Purpose of the Study:

  • To evaluate the impact of boundary objects (BOS) on the accuracy and reliability of left ventricular (LV) identification.
  • To analyze the types and causes of errors in LV identification processes.

Main Methods:

  • Comparative analysis of LV identification success rates with and without the use of BOS.
  • Classification of errors into undetected LVs (minor) and misclassified LVs (major).

Main Results:

  • The success rate for LV identification nearly doubles when BOS are employed, reaching 90% accuracy.

Related Experiment Videos

  • Undetected LVs (minor errors) occur in 7.4% of cases due to unadapted descriptions or new BOS.
  • Misclassification errors (major errors) account for 2.8% of cases, stemming from statistical classification or unmodelled BOS.

    • Conclusions:

    • Boundary objects (BOS) significantly enhance the performance of left ventricular (LV) identification systems.
    • Strategies for error reduction include updating graphical models and refining classification techniques.