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 comparison of some quick and simple threshold selection methods for stained cells.

C MacAulay1, B Palcic

  • 1British Columbia Cancer Research Center, Vancouver, Canada.

Analytical and Quantitative Cytology and Histology
|April 1, 1988
PubMed
Summary

Four simple gray-scale thresholding methods were evaluated for segmenting cervical cell images. Postprocessing enhanced nuclear segmentation accuracy, with the best method achieving 81% cytoplasm and 78% nuclei segmentation.

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

Multipath artifacts enable angular contrast in multimodal endoscopic optical coherence tomography.

Optics express·2024
Same author

Triple-clad W-type fiber mitigates multipath artifacts in multimodal optical coherence tomography.

Optics express·2023
Same author

Economic evaluation of DNA ploidy analysis vs liquid-based cytology for cervical screening.

British journal of cancer·2015
Same author

Autofluorescence imaging can identify preinvasive or clinically occult lesions in fallopian tube epithelium: a promising step towards screening and early detection.

Gynecologic oncology·2011
Same author

Optical properties of normal and carcinomatous bronchial tissue.

Applied optics·2010
Same author

Optical memory disks in image data-base management for cytometry.

Applied optics·2010

Area of Science:

  • Medical image analysis
  • Computational pathology
  • Cytology automation

Background:

  • Accurate segmentation of cervical cells is crucial for automated analysis.
  • Existing segmentation methods vary in speed and accuracy.
  • Gray-scale thresholding offers a potentially fast approach.

Purpose of the Study:

  • To compare the segmentation accuracy of four fast, simple gray-scale threshold selection methods.
  • To evaluate the impact of postprocessing on nuclear segmentation.
  • To identify optimal methods for cervical cell image segmentation.

Main Methods:

  • A database of stained cervical cell images was utilized.
  • Four distinct gray-scale threshold selection algorithms were implemented.

Related Experiment Videos

  • Image segmentation was performed, followed by postprocessing steps.
  • Accuracy was assessed based on correct segmentation of cytoplasm and nuclei.

    • Main Results:

    • The study compared the performance of four thresholding techniques.
    • Postprocessing significantly improved nuclear segmentation accuracy.
    • The most effective method achieved 81% cytoplasm segmentation accuracy.
    • The leading method demonstrated 78% nuclear segmentation accuracy.

    Conclusions:

    • Simple gray-scale thresholding methods can be effective for cervical cell segmentation.
    • Postprocessing is vital for enhancing nuclear segmentation precision.
    • The optimal method identified provides a foundation for automated cytologic analysis.