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

Optimizing cervical cell classifiers

K R Castleman, B S White

    Analytical and Quantitative Cytology
    |June 1, 1980
    PubMed
    Summary
    This summary is machine-generated.

    Optimizing automated prescreening systems requires careful error rate balancing. For cell classifiers, a low false-positive rate is crucial, unlike specimen classifiers, to minimize sample size and meet error rate goals.

    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

    ClonEvol: clonal ordering and visualization in cancer sequencing.

    Annals of oncology : official journal of the European Society for Medical Oncology·2017
    Same author

    U2AF1 mutations alter sequence specificity of pre-mRNA binding and splicing.

    Leukemia·2014
    Same author

    Clonal diversity of recurrently mutated genes in myelodysplastic syndromes.

    Leukemia·2013
    Same author

    Spatial and photometric resolution and calibration requirements for cell image analysis instruments.

    Applied optics·2010
    Same author

    Two-dimensional image processing and analysis.

    Current protocols in cytometry·2008
    Same author

    Cameras.

    Current protocols in cytometry·2008
    Same journal

    Chromatin pattern and DNA content in acquired immune deficiency syndrome (AIDS): indicators of viral infection revealed by DNA image cytometry.

    Analytical and quantitative cytology·1984
    Same journal

    Quantitative analysis of heterogeneity of estrogen binding in human breast tumor specimens.

    Analytical and quantitative cytology·1984
    Same journal

    Analysis of number, size and distribution patterns of lipid vacuoles in benign and malignant mesothelial cells.

    Analytical and quantitative cytology·1984
    Same journal

    Automated measurement of acid phosphatase reaction product in human kidneys treated with aminoglycoside antibiotics.

    Analytical and quantitative cytology·1984
    Same journal

    The use of cationic polyelectrolytes in the preparation of cell monolayers for automated cell scanning and diagnostic cytopathology.

    Analytical and quantitative cytology·1984
    Same journal

    Simulation model for gynecologic specimen classification in a high-resolution prescreening system.

    Analytical and quantitative cytology·1984
    See all related articles

    Area of Science:

    • * Computational pathology
    • * Medical image analysis
    • * Machine learning in healthcare

    Background:

    • * Automated prescreening systems utilize cascaded classifiers (cell and specimen) for performance optimization.
    • * Balancing false-positive and false-negative rates is critical for overall system efficacy.
    • * Typically, specimen classifiers aim for lower false-negative than false-positive rates.

    Purpose of the Study:

    • * To analyze the optimal operating points for cascaded classifiers in automated prescreening.
    • * To determine the ideal trade-off between false-positive and false-negative rates for cell classifiers.
    • * To develop a method for minimizing sample size while achieving specific specimen error rates.

    Main Methods:

    • * Analysis of classifier cascade performance based on error rate trade-offs.

    Related Experiment Videos

  • * Receiver Operating Characteristic (ROC) curve analysis for cell classifier optimization.
  • * Development of a procedure for selecting optimal operating points.

    • Main Results:

    • * Cell classifiers require a significantly lower false-positive rate compared to their false-negative rate.
    • * The analysis contrasts with the typical desirable operating point for specimen classifiers.
    • * A procedure was established to identify the optimal cell classifier operating point.

    Conclusions:

    • * Strategic adjustment of cell classifier error rates is essential for efficient automated prescreening.
    • * The proposed method optimizes performance and reduces the necessary sample size.
    • * Findings guide the development of more effective computational pathology tools.