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

Linear structures in mammographic images: detection and classification.

Reyer Zwiggelaar1, Susan M Astley, Caroline R M Boggis

  • 1Department of Computer Science, University of Wales, Aberystwyth, Ceredigion SY23 3DB, UK. rrz@aber.ac.uk

IEEE Transactions on Medical Imaging
|September 21, 2004
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

A Systematic Evidence Map of FAIR Compliance in Open-Access Metabolomics Research: Results from a Pilot Study.

Studies in health technology and informatics·2026
Same author

Predicting Lung Function from Voice Recordings Using Machine Learning: An Optimised Approach.

Studies in health technology and informatics·2026
Same author

Deep learning models to predict mammographic density jointly on standard dose and low dose images.

The British journal of radiology·2026
Same author

Biocatalytic Production of a Key Chiral Intermediate of the HIV Capsid Inhibitor Lenacapavir.

Journal of the American Chemical Society·2026
Same author

Can I Do Better Than AI: A Comparative Analysis of a Medical Student Essay Created With and Without Generative AI.

Cureus·2026
Same author

Change in mammographic density as a potential predictor of cancer recurrence after breast conservation surgery and adjuvant endocrine therapy: results of the MEDICI study.

Breast cancer research : BCR·2026

This study introduces advanced methods for detecting and classifying linear structures in mammograms, improving the accuracy of identifying abnormalities like spicules and ducts for better cancer detection.

Area of Science:

  • Medical Imaging
  • Radiology
  • Computer-Aided Diagnosis

Background:

  • Mammography is crucial for breast cancer screening.
  • Accurate detection of subtle linear abnormalities like spicules and ducts remains challenging.
  • Improving specificity in abnormality detection can reduce false positives.

Purpose of the Study:

  • To develop and compare methods for detecting linear structures in mammograms.
  • To classify detected linear structures into anatomical types.
  • To enhance the specificity of mammographic abnormality detection.

Main Methods:

  • Comparison of multiple linear structure detection algorithms using synthetic mammograms.
  • Receiver Operating Characteristic (ROC) analysis for performance evaluation.

Related Experiment Videos

  • Classification of detected structures based on cross-sectional profiles and shape attributes.

    • Main Results:

    • Significant differences observed between detection methods (p < 0.001).
    • Best detection method achieved a pixel-level detection Az value of 0.943.
    • Automatic classification demonstrated useful discrimination between anatomical classes (Az = 0.746), with profile shape providing key information (Az = 0.653).

    Conclusions:

    • The developed methods effectively detect and classify linear structures in mammograms.
    • Exploiting anatomical information from linear structures improves abnormality detection specificity.
    • These techniques hold potential for enhancing mammographic screening accuracy.