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

Method for counting mitoses by image processing in Feulgen stained breast cancer sections

T K ten Kate1, J A Beliën, A W Smeulders

  • 1Department of Pathology, Free University, Amsterdam, The Netherlands.

Cytometry
|January 1, 1993
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

Discrete representation of straight lines.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Best linear unbiased estimators for properties of digitized straight lines.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Quantitative immunohistochemistry of estrogen and progesterone receptor positivity in ovarian tumors : a rapid and reliable stereological approach.

Methods in molecular medicine·2011
Same author

Accuracy of optical density measurement of cells. 1: Low resolution.

Applied optics·2010
Same author

Potential clinical uses of laser scan microscopy.

Applied optics·2010
Same author

PicToSeek: combining color and shape invariant features for image retrieval.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2008

An automated image analysis method for breast cancer mitotic counting shows promise. While fully automatic classification achieved 81% accuracy, a semiautomated approach with interactive evaluation offers a more reliable prescreening tool for clinical use.

Area of Science:

  • Pathology
  • Computational Biology
  • Medical Imaging

Background:

  • Accurate mitotic count is crucial for breast cancer prognosis.
  • Manual assessment of mitotic figures is subjective and time-consuming.
  • Image processing offers potential for objective and efficient mitotic count assessment.

Purpose of the Study:

  • To develop and evaluate an automated image processing method for mitotic count assessment in Feulgen-stained breast cancer sections.
  • To compare the performance of a fully automatic method with a semiautomated method involving interactive evaluation.

Main Methods:

  • Feulgen-stained breast cancer tissue sections were analyzed using an optimized image segmentation procedure.
  • Contour features and optical density measurements were computed for object classification.

Related Experiment Videos

  • A training set of nine specimens and an independent test set of three specimens were used.
  • Performance was evaluated by comparing automated counts with interactive counting and morphometry.

    • Main Results:

    • The segmentation procedure effectively removed non-mitotic objects but also eliminated 11% of mitotic figures.
    • The fully automatic method achieved 81% correct classification of mitoses at the specimen level, with 30% false positives.
    • A strong correlation (r = 0.98) was observed between the fully automatic and interactive counting procedures.
    • The semiautomated method, with interactive evaluation, showed an almost perfect correlation (r = 0.998) with interactive morphometry.

    Conclusions:

    • The fully automatic image processing method, while promising, is not yet suitable for direct clinical application due to false positives.
    • The semiautomated method, integrating interactive evaluation, provides an accurate reflection of mitotic counts and shows potential as a prescreening device in clinical practice.