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

A knowledge-based boundary delineation system for contrast ventriculograms.

L Sui1, R M Haralick, F H Sheehan

  • 1Ultrasound Group, Siemens Medical System, Issaquah, WA 98029, USA.

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|June 26, 2001
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

[Analysis of the efficacy and safety of laser therapy for high-grade anal intraepithelial neoplasia in HIV-negative women].

Zhonghua fu chan ke za zhi·2026
Same author

[Correlation study of blood lipid indexes and body mass index with clinical characteristics of cervical squamous cell carcinoma].

Zhonghua fu chan ke za zhi·2026
Same author

[Value of self-sampling cervical exfoliated cells of HPV E6/E7 mRNA detection in cervical cancer screening: a multicenter clinical study].

Zhonghua fu chan ke za zhi·2026
Same author

[Expert consensus on the clinical application of endometrial ablation].

Zhonghua fu chan ke za zhi·2025
Same author

[Value of laser therapy, photodynamic therapy, and follow-up observation in the management of cervical low-grade squamous intraepithelial lesions: a prospective cohort study].

Zhonghua fu chan ke za zhi·2024
Same author

[Clinical effect of secondary LEEP combined with transcervical resection of endocervical tissue for cervical precancerous lesions with positive internal margin after the first LEEP].

Zhonghua fu chan ke za zhi·2024

This study introduces an automated method for delineating the left ventricle (LV) boundary in contrast ventriculograms, achieving accuracy close to human experts. The novel approach significantly improves automated LV boundary detection in cardiac imaging.

Area of Science:

  • Cardiology
  • Medical Imaging
  • Biomedical Engineering

Background:

  • Automated left-ventricle (LV) boundary delineation from contrast ventriculograms remains a challenge.
  • Existing methods lack the required accuracy for clinical application.

Purpose of the Study:

  • To develop and validate a novel knowledge-based, multistage method for automated LV boundary delineation at end diastole (ED) and end systole (ES).
  • To assess the accuracy of the proposed method against manual tracings and interobserver variability.

Main Methods:

  • A multistage approach incorporating multiimage pixel region classification, shape regression, and rejection classification.
  • Extensive use of knowledge regarding LV shape and dynamics.
  • Training and cross-validation on a database of 375 contrast ventriculogram studies with manually traced boundaries.

Related Experiment Videos

Main Results:

  • Achieved a mean absolute boundary error of approximately 2 mm.
  • Associated ejection fraction error was approximately 6%.
  • Cross-validated accuracy demonstrated performance close to and slightly exceeding interobserver variability.

Conclusions:

  • The developed knowledge-based multistage method offers accurate automated LV boundary delineation in contrast ventriculograms.
  • This method shows potential to approach and surpass human observer variability, advancing cardiac image analysis.
  • The findings suggest a significant step forward in automated analysis of cardiac function from ventriculography.