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 statistical methodology for mammographic density detection.

J J Heine1, R P Velthuizen

  • 1Department of Radiology, College of Medicine, The University of South Florida, and the H. Lee Moffitt Cancer Center and Research Institute, Tampa 33612-4799, USA. heine@splinter.usf.edu

Medical Physics
|February 24, 2001
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

Calibrated breast density methods for full field digital mammography: a system for serial quality control and inter-system generalization.

Medical physics·2015
Same author

Breast Imaging Reporting and Data System (BI-RADS) breast composition descriptors: automated measurement development for full field digital mammography.

Medical physics·2013
Same author

On the statistical nature of mammograms.

Medical physics·1999
Same author

Feature extraction for MRI segmentation.

Journal of neuroimaging : official journal of the American Society of Neuroimaging·1999
Same author

Review and evaluation of MRI nonuniformity corrections for brain tumor response measurements.

Medical physics·1998
Same author

MRI measurement of brain tumor response: comparison of visual metric and automatic segmentation.

Magnetic resonance imaging·1998
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
Same journal

A novel optical respiratory gating system with a hybrid phase-amplitude algorithm for spot-scanning proton therapy.

Medical physics·2026
Same journal

Gamma Knife treatment planning using knowledge-based reinforcement learning.

Medical physics·2026
Same journal

Development and characterization of a novel, small animal external beam irradiator using a clinical high dose rate brachytherapy source.

Medical physics·2026
Same journal

Deep learning-based dose prediction for MR-guided prostate SIB: Supporting rapid feasibility assessment and adaptive editing margin selection.

Medical physics·2026
See all related articles

A new statistical method uses chi-square analysis to automatically distinguish fat from fibroglandular tissue in mammograms. This technique aids in breast cancer risk assessment by analyzing tissue density from digital images.

Area of Science:

  • Medical Imaging
  • Biostatistics
  • Radiology

Background:

  • Mammographic density is a recognized breast cancer risk factor.
  • Accurate quantification of breast tissue composition is crucial for risk assessment.
  • Existing methods may lack automated and precise tissue discrimination capabilities.

Purpose of the Study:

  • To develop and validate a statistical methodology for automated discrimination of fat and fibroglandular tissue in digitized mammograms.
  • To establish a foundation for incorporating tissue density into breast cancer risk analysis.
  • To enable quantitative analysis of breast tissue composition directly from image data.

Main Methods:

  • A chi-square probability analysis based statistical methodology is employed.
  • The method utilizes a reversible linear filtering operation analogous to deconvolution.

Related Experiment Videos

  • A relaxation method estimates a global reference variance, with local variances compared using chi-square analysis to label tissue as fat or nonfat.

    • Main Results:

    • The methodology successfully discriminates between radiolucent (fat) and dense (fibroglandular) tissues.
    • Preliminary results demonstrate encouraging accuracy in region-by-region tissue labeling.
    • The approach identifies two distinct random events in the input field with differing variances, corresponding to fat and other tissues.

    Conclusions:

    • The developed statistical method offers automated and reliable discrimination of breast tissue types in mammograms.
    • This technique provides a basis for integrating mammographic density into breast cancer risk assessment models.
    • Future applications include quantitative risk analysis based on fat/dense tissue percentages and amounts.