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 probabilistic expert system that provides automated mammographic-histologic correlation: initial experience.

Elizabeth S Burnside1, Daniel L Rubin, Ross D Shachter

  • 1Department of Radiology, University of California School of Medicine, Box 1667, San Francisco, CA 94143-1667, USA. bburnside@mail.radiology.wisc.edu

AJR. American Journal of Roentgenology
|January 23, 2004
PubMed
Summary

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

Extraction of distant recurrence sites for breast cancer patients from free-text clinical notes using large language models.

Journal of biomedical informatics·2026
Same author

Psychological safety in interdisciplinary teams: how leadership behaviors empower teams.

Frontiers in psychology·2026
Same author

A Pragmatic Randomized Controlled Trial of Ambient Artificial Intelligence to Improve Health Practitioner Well-Being.

NEJM AI·2026
Same author

Creation of Radiology Teaching Content with STELLA-A STandardized Electronic Learning Library and Application Platform.

Academic radiology·2025
Same author

Managing Bleeding Risks and Complications of Imaging-guided Breast Biopsy: A Primer for Radiologists.

Radiographics : a review publication of the Radiological Society of North America, Inc·2025
Same author

Large-scale meta-analysis and precision functional assays identify FANCM regions in which PTVs confer different risks for ER-negative and triple-negative breast cancer.

Breast (Edinburgh, Scotland)·2025

A new expert system accurately correlates mammographic findings with breast biopsy results, aiding radiologists in detecting potential sampling errors. This AI tool enhances diagnostic accuracy for breast cancer screening.

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Pathology and Diagnostic Accuracy

Background:

  • Assessing concordance between mammographic findings and biopsy results is crucial for accurate breast cancer diagnosis.
  • Radiologists face challenges in consistently correlating imaging findings with histopathology.
  • Automated systems may improve the accuracy and efficiency of this correlation process.

Purpose of the Study:

  • To evaluate a probabilistic expert system for automated imaging-histologic correlation in breast biopsies.
  • To determine if the system can assist radiologists in identifying discordant findings.
  • To assess the system's ability to detect potential biopsy sampling errors.

Main Methods:

  • A Bayesian network was developed, linking Breast Imaging Reporting and Data System (BI-RADS) descriptors to breast diseases.

Related Experiment Videos

  • Mammographic findings updated pretest probabilities to posttest probabilities using Bayes' theorem.
  • The system was evaluated on 92 imaging-guided breast biopsies, comparing automated correlations with radiologist assessments.

    • Main Results:

    • The expert system achieved 100% sensitivity and 91% specificity in identifying incorrect pathologic diagnoses.
    • The system successfully integrated pathology and mammography data to calculate probabilities of sampling error.
    • A sampling error rate of 1.1% was observed in the evaluated biopsies.

    Conclusions:

    • The probabilistic expert system shows potential in aiding radiologists to identify discordant breast biopsy results.
    • The system can help detect cases where biopsy sampling errors may have occurred.
    • Automated correlation tools can enhance diagnostic confidence and patient care in breast imaging.