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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Tandem repeat polymorphisms are associated with brain structure: results of two large population-based studies.

Genome medicine·2026
Same author

Spin-State Transition in Heterometal-Bridged Cu-MnN<sub>4</sub> Motifs Overcomes Activity-Stability Trade-Off for Ultra-Stable Zinc-Air Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Research Progress in the Preparation of Lactide.

Polymers·2026
Same author

Biomaterial-Integrated Electroporation for Therapeutic Delivery: From Gene Editing to Tumor Ablation and Immune Modulation.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Reconstruction from multi-planar MRI with foundation models for uterine fibroid analysis.

NPJ digital medicine·2026
Same author

A new and eco-friendly disinfectant for antimicrobial-resistant bacteria: ozone nano water.

BMC microbiology·2026

Related Experiment Video

Updated: Jul 18, 2025

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K

Mammographic Breast Density Model Using Semi-Supervised Learning Reduces Inter-/Intra-Reader Variability.

Alyssa T Watanabe1,2, Tara Retson3, Junhao Wang2

  • 1Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90007, USA.

Diagnostics (Basel, Switzerland)
|August 26, 2023
PubMed
Summary
This summary is machine-generated.

A deep learning (DL) model significantly reduced variability and reading time in mammographic density assessment, improving consistency for radiologists. This AI tool enhances diagnostic accuracy and efficiency in breast cancer risk evaluation.

Keywords:
automated breast densitydeep learningmammographyreader variability

More Related Videos

Quantification of Breast Cancer Cell Invasiveness Using a Three-dimensional 3D Model
08:08

Quantification of Breast Cancer Cell Invasiveness Using a Three-dimensional 3D Model

Published on: June 11, 2014

15.9K
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

42.9K

Related Experiment Videos

Last Updated: Jul 18, 2025

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K
Quantification of Breast Cancer Cell Invasiveness Using a Three-dimensional 3D Model
08:08

Quantification of Breast Cancer Cell Invasiveness Using a Three-dimensional 3D Model

Published on: June 11, 2014

15.9K
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

42.9K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Oncology

Background:

  • Breast density is a key breast cancer risk factor.
  • Inconsistent reporting of mammographic density by radiologists causes confusion.
  • Standardized breast density assessment is crucial for accurate risk stratification.

Purpose of the Study:

  • To evaluate a deep learning (DL) model for mammographic density grading.
  • To assess the impact of the DL model on inter- and intra-reader variability.
  • To determine the effect of the DL model on radiologist reading time.

Main Methods:

  • Retrospective multi-reader, multi-case study with 928 mammogram pairs.
  • Seven readers assessed density initially, then reread images aided by the DL model.
  • Linear Cohen Kappa (κ) and Student's t-test were used for statistical analysis.

Main Results:

  • The DL model achieved high accuracy (κ=0.87 for 4-class, κ=0.91 for binary).
  • DL assistance significantly reduced inter-reader variability (κ improved from 0.70 to 0.88) and intra-reader variability (κ improved from 0.83 to 0.95).
  • Average reading time per image pair decreased by 30% (0.86 s).

Conclusions:

  • Deep learning models can significantly improve consistency in mammographic density assessment.
  • AI-powered tools enhance diagnostic accuracy and efficiency for radiologists.
  • DL assistance in mammography has the potential to reduce diagnostic errors and improve patient care.