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 Video

Updated: May 13, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

A comprehensive methodology for determining the most informative mammographic features.

Yirong Wu1, Oguzhan Alagoz, Mehmet U S Ayvaci

  • 1Department of Radiology, University of Wisconsin School of Medicine and Public Health, E3/311 Clinical Science Center, 600 Highland Avenue, Madison, WI, 53792-3252, USA.

Journal of Digital Imaging
|March 19, 2013
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

Age, morphology, and environmental variation shape movement behaviour syndromes in a riverine fish - golden perch (Macquaria ambigua).

Movement ecology·2026
Same author

Enhancing the OncoSim-Breast model using Canadian breast density information.

Health reports·2026
Same author

Do Quality-Adjusted-Life-Year-Based Cost-Effectiveness Analyses Discriminate Against Disabled Patients? A Theoretical and Empirical Analysis.

Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research·2026
Same author

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

Frontiers in psychology·2026
Same author

Outcomes of Density-Targeted Supplemental Breast Magnetic Resonance Imaging Screening by Breast Cancer Risk: Long-Term Health and Economic Considerations.

Annals of internal medicine·2026
Same author

Overdiagnosis of Papillary Thyroid Cancer.

JAMA network open·2026

Mass margins and shape are the most informative mammographic features for accurate breast cancer diagnosis, according to mutual information analysis. This study identified key indicators for improved diagnostic efficiency.

Area of Science:

  • Radiology and Medical Imaging
  • Biostatistics
  • Machine Learning in Healthcare

Background:

  • Accurate breast cancer diagnosis relies on interpreting complex mammographic features.
  • Identifying the most predictive features can enhance diagnostic accuracy and efficiency.
  • Mutual Information (MI) offers a quantitative approach to assess feature informativeness.

Purpose of the Study:

  • To determine the most informative mammographic features for breast cancer diagnosis using MI analysis.
  • To rank mammographic features based on their predictive value for malignancy.
  • To validate MI findings with machine learning classifier performance.

Main Methods:

  • Utilized a large dataset of 44,397 mammography reports from 20,375 patients.

More Related Videos

Clinical Imaging of Microwave Mammography
05:28

Clinical Imaging of Microwave Mammography

Published on: November 14, 2025

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Related Experiment Videos

Last Updated: May 13, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Clinical Imaging of Microwave Mammography
05:28

Clinical Imaging of Microwave Mammography

Published on: November 14, 2025

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

  • Calculated MI using Shannon's entropy to assess feature informativeness against diagnosis.
  • Trained and validated Naïve Bayes classifiers using tenfold cross-validation and AUC to evaluate feature rankings.

    • Main Results:

    • Mass margins and mass shape were identified as the most informative features for breast cancer diagnosis.
    • Calcification morphology, mass density, and calcification distribution also provided significant predictive information.
    • Breast composition and associated findings offered minimal diagnostic value.

    Conclusions:

    • MI analysis effectively ranks mammographic features for breast cancer diagnosis.
    • Mass margins and shape are crucial indicators for differentiating benign from malignant findings.
    • This framework supports the development of more accurate and efficient breast cancer diagnostic tools.