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-designed expert systems for breast cytology diagnosis

W H Wolberg1, O L Mangasarian

  • 1Department of Surgery, University of Wisconsin-Madison.

Analytical and Quantitative Cytology and Histology
|February 1, 1993
PubMed
Summary

Expert systems accurately diagnose breast cancer from fine needle aspiration cytology, achieving high sensitivity and specificity in initial tests and clinical application for breast mass evaluation.

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

Successive overrelaxation for support vector machines.

IEEE transactions on neural networks·2008
Same author

Nonlinear knowledge in kernel approximation.

IEEE transactions on neural networks·2007
Same author

Importance of nuclear morphology in breast cancer prognosis.

Clinical cancer research : an official journal of the American Association for Cancer Research·1999
Same author

Computer-derived nuclear features compared with axillary lymph node status for breast carcinoma prognosis.

Cancer·1997
Same author

Indeterminate fine-needle aspiration of the breast. Image analysis-assisted diagnosis.

Cancer·1997
Same author

Computer-derived nuclear "grade" and breast cancer prognosis.

Analytical and quantitative cytology and histology·1995

Area of Science:

  • Oncology
  • Medical Informatics
  • Cytopathology

Background:

  • Accurate diagnosis of breast masses is crucial for effective cancer treatment.
  • Fine needle aspiration (FNA) cytology is a common diagnostic tool.
  • Limitations in human interpretation can affect diagnostic accuracy.

Purpose of the Study:

  • To develop and evaluate expert systems for diagnosing breast masses using FNA cytology.
  • To assess the sensitivity and specificity of these AI systems compared to clinical evaluation.

Main Methods:

  • Development of three expert systems based on nine visually assigned scalar values of epithelial cells from breast FNA.
  • Application of the expert systems to analyze 804 breast masses.
  • Comparison of expert system diagnostic performance with clinical assessment.

Main Results:

  • Expert systems achieved high diagnostic performance with up to 0.98 sensitivity and 0.97 specificity in initial evaluations.
  • Clinical application on 804 breast masses showed 0.98 sensitivity and 0.93 specificity.
  • A small percentage (0.04) of aspirates were unsatisfactory for analysis.

Conclusions:

  • Expert systems demonstrate significant potential for accurate breast cancer diagnosis from FNA cytology.
  • The AI-driven approach offers high sensitivity and specificity, aiding in clinical decision-making.
  • Discrepancies between AI and clinical specificity highlight challenges like sampling errors during aspiration.

Related Experiment Videos