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

Computerized image analysis: estimation of breast density on mammograms.

C Zhou1, H P Chan, N Petrick

  • 1Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109-0030, USA.

Medical Physics
|July 7, 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

FOXP3-stained image analysis for follicular lymphoma: Optimal adaptive thresholding with maximal nucleus coverage.

Proceedings of SPIE--the International Society for Optical Engineering·2017
Same author

WE-E-217A-02: Methodologies for Evaluation of Standalone CAD System Performance.

Medical physics·2017
Same author

Search for new phenomena in events with at least three photons collected in <i>pp</i> collisions at [Formula: see text] = 8 TeV with the ATLAS detector.

The European physical journal. C, Particles and fields·2017
Same author

A measurement of the calorimeter response to single hadrons and determination of the jet energy scale uncertainty using LHC Run-1 <i>pp</i>-collision data with the ATLAS detector.

The European physical journal. C, Particles and fields·2017
Same author

Measurement of the [Formula: see text] and [Formula: see text] production cross sections in multilepton final states using 3.2 fb[Formula: see text] of [Formula: see text] collisions at [Formula: see text] = 13 TeV with the ATLAS detector.

The European physical journal. C, Particles and fields·2017
Same author

Effect of miR-212 targeting TCF7L2 on the proliferation and metastasis of cervical cancer.

European review for medical and pharmacological sciences·2017

An automated tool estimates mammographic breast density, aiding risk assessment and monitoring. This computer vision approach shows high accuracy, outperforming subjective radiologist assessments for improved breast density analysis.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Radiology

Background:

  • Mammographic breast density is a key factor in breast cancer risk assessment.
  • Current visual assessment methods by radiologists are subjective and can lack reproducibility.
  • Automated tools are needed to improve the accuracy and consistency of breast density estimation.

Purpose of the Study:

  • To develop and evaluate an automated image analysis tool for estimating mammographic breast density.
  • To assess the tool's performance against manual segmentation by radiologists.
  • To explore the potential of computer vision for objective breast density analysis.

Main Methods:

  • Automated segmentation of breast regions using a boundary-tracking algorithm.
  • Adaptive dynamic range compression to enhance image features.

Related Experiment Videos

  • Rule-based classification of breast density based on gray level histogram analysis.
  • Computer-estimated percent dense area compared to radiologist-averaged manual segmentation.

    • Main Results:

    • High correlation (0.94 CC, 0.91 MLO) between automated and manual breast density estimations for correctly classified images.
    • Mean bias of automated estimation was less than 2%, significantly lower than radiologists' mean bias (0.1%–11%).
    • Minor misclassification rate (6%) observed, indicating the algorithm's robustness.

    Conclusions:

    • The developed automated tool demonstrates feasibility for accurate mammographic breast density estimation.
    • Computer vision techniques offer potential for improved accuracy and reproducibility compared to subjective visual assessment.
    • This tool could enhance breast cancer risk stratification and monitoring in clinical practice.