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 selective mapping algorithm for computer analysis of voided urine cell images.

E K Wong1, E H Liang, E K Lin

  • 1Department of Electrical Engineering and Computer Science, Polytechnic University, Brooklyn, New York.

Analytical and Quantitative Cytology and Histology
|June 1, 1989
PubMed
Summary

An automated selective mapping algorithm reduces errors in cytologic image analysis by selecting relevant cells at low power for high-resolution review. This improves the accuracy of automated cell classification in diagnostic evaluations.

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

Near-Monochromatic Tuneable Cryogenic Niobium Electron Field Emitter.

Physical review letters·2022
Same author

Development and validation of a prognostic model for overall survival in chemotherapy-naïve men with metastatic castration-resistant prostate cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2018
Same author

Brain early infarct detection using gamma correction extreme-level eliminating with weighting distribution.

Scanning·2016
Same author

A forebrain-retrorubral pathway involved in male sex behavior is GABAergic and activated with mating in gerbils.

Neuroscience·2010
Same author

Automated image analysis in the diagnosis of bladder cancer.

Applied optics·2010
Same author

Harry m. Zimmerman, m.d. (1901-1995).

The American journal of pathology·2009

Area of Science:

  • * Medical image analysis
  • * Computational pathology
  • * Cytology automation

Background:

  • * Automated image analysis in cytology aims to minimize classification errors caused by unsegmentable or misleading cellular features.
  • * Previous efforts involved hierarchical analysis of microscopic objects at high resolution.
  • * This study introduces a novel automated algorithm for improved cell selection and analysis.

Purpose of the Study:

  • * To develop and implement an automated selective mapping algorithm for cytologic preparations.
  • * To reduce classification errors by efficiently selecting relevant cells for further analysis.
  • * To enhance the diagnostic evaluation of urine sediments using automated image analysis.

Main Methods:

  • * Development of an automated "selective mapping algorithm" for low-power cell selection.

Related Experiment Videos

  • * Feature extraction from 256 x 240 digital images using a 10x planachromatic objective.
  • * Implementation of a five-node binary tree classifier for object triage.
  • * Integration into a video-based image analysis system for urine sediment evaluation.

    • Main Results:

    • * Initial testing on 501 objects yielded a 61.3% correct acceptance rate and 81.3% correct rejection rate.
    • * In a preliminary evaluation on urine sediments, the algorithm selected up to 100 objects per case.
    • * Of 810 selected objects, 344 (42.5%) were classified as diagnostically valuable cells.

    Conclusions:

    • * The selective mapping algorithm successfully identifies and selects cells for further analysis, reducing the burden on high-power classification.
    • * This automated approach shows promise for improving the efficiency and accuracy of cytologic diagnostic evaluations.
    • * Further integration and testing are warranted for widespread clinical application.