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

Computer recognition of binucleation with overlapping in epithelial cells.

J J Sychra, P H Bartels, M Bibbo

    Acta Cytologica
    |January 1, 1978
    PubMed
    Summary

    A new computer technique accurately identifies binucleation, a condition with two nuclei, in epithelial cells. This method analyzes nuclear shape features for reliable detection, matching human visual assessment.

    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 PC-based system for the objective analysis of histologic specimens through quantitative contextual karyometry.

    Applied optics·2010
    Same author

    Knowledge engineering in quantitative histopathology.

    Applied optics·2010
    Same author

    Computers or cytotechnologists?

    Acta cytologica·1999
    Same author

    Cerebral perfusion SPECT imaging in epileptic and nonepileptic seizures.

    Clinical nuclear medicine·1997
    Same author

    Automated screening for cervical cancer: diagnostic decision procedures.

    Acta cytologica·1997
    Same author

    Compton scatter correction in case of multiple crosstalks in SPECT imaging.

    Neurological research·1996

    Area of Science:

    • Biomedical image analysis
    • Computational pathology
    • Cell biology

    Background:

    • Binucleation, characterized by the presence of two nuclei within a single cell, is a significant cytological feature.
    • Accurate detection of binucleation is crucial for various diagnostic and research applications in cell biology.
    • Existing methods for binucleation detection may face challenges with overlapping nuclei.

    Purpose of the Study:

    • To develop and evaluate a novel computer-based technique for the automated recognition of binucleation in epithelial cells, specifically addressing overlapping nuclei.
    • To assess the performance of the developed algorithm against human visual inspection.

    Main Methods:

    • The computer program utilizes analytic features derived solely from the nuclear contour.

    Related Experiment Videos

  • The feature set incorporates moments, Fourier transform features, and linguistic features for comprehensive analysis.
  • The algorithm was designed to process images of epithelial cells for binucleation detection.

    • Main Results:

    • The developed computer technique demonstrated satisfactory performance in recognizing binucleation.
    • The algorithm's accuracy was comparable to human visual assessment, even in cases with overlapping nuclei.
    • The analysis focused on nuclear contour features, proving effective for binucleation identification.

    Conclusions:

    • The proposed computer recognition technique offers a reliable method for detecting binucleation in epithelial cells.
    • The algorithm's reliance on nuclear contour features provides a robust approach, particularly for challenging cases with overlapping nuclei.
    • This automated method holds potential for enhancing efficiency and accuracy in cytological analysis.