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

Measuring image texture to separate "difficult" from "easy" mammograms

P Taylor1, S Hajnal, M H Dilhuydy

  • 1Advanced Computation Laboratory, Imperial Cancer Research Fund, London, UK.

The British Journal of Radiology
|May 1, 1994
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

[Assessment of the dense breast within the French screening program: the role of ultrasonography].

Journal de radiologie·2008
Same author

[Elastography of the breast: a prospective study of 122 lesions].

Journal de radiologie·2007
Same author

[How I perform a breast MRI].

Journal de radiologie·2007
Same author

[Bilateral ductal carcinoma in situ of the breast: independent events or bilateral disease?].

Journal de gynecologie, obstetrique et biologie de la reproduction·2007
Same author

[Communicating the results in breast oncology: nonverbal and verbal exchange].

Journal de radiologie·2007
Same author

[Communicating the results of the BI-RADS categories to patients in senology].

Journal de radiologie·2007

Computerized analysis can automatically sort mammograms by breast tissue density. This technique identifies fatty tissue, improving radiologist efficiency and computer-aided detection for breast cancer screening.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Radiology

Background:

  • Mammogram interpretation is challenging due to variations in breast tissue density.
  • Dense breast tissue can obscure abnormalities, complicating diagnosis for both radiologists and computer-aided detection (CAD) systems.
  • Efficient allocation of expert radiologist time is crucial for effective breast cancer screening.

Purpose of the Study:

  • To develop and validate computerized techniques for automatically classifying mammograms based on breast tissue density (fatty vs. dense).
  • To improve the efficiency of mammogram interpretation and the performance of CAD systems.
  • To enable better utilization of expert radiologists' skills by prioritizing difficult cases.

Main Methods:

  • Mammograms were independently classified as fatty or dense by two radiologists.

Related Experiment Videos

  • Local statistical and texture measures were computed from digitized mammogram patches.
  • A specific measure, local skewness in tiles, was identified as effective for distinguishing fatty from dense tissue.

    • Main Results:

    • The local skewness measure demonstrated significant separation between fatty and dense breast tissue patches.
    • An automated procedure incorporating this measure successfully classified approximately two-thirds of fatty mammograms.
    • The findings were validated on mammograms from a UK screening program.

    Conclusions:

    • Automated classification of mammograms by breast tissue density is feasible using texture analysis.
    • This technology can enhance radiologist workflow and improve the effectiveness of computer-aided detection.
    • The study provides a robust method for identifying mammograms with fatty tissue, facilitating targeted analysis.