Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

[Effects of Japanese Green Tea on the Brain: Prevention of Aging].

Brain and nerve = Shinkei kenkyu no shinpo·2026

Same author

IL-31 blockade elevates thymus and activation-regulated chemokine by lifting LAMP3<sup>+</sup>CD1c<sup>+</sup> mature dendritic cells from calcitonin gene-related peptide-calcitonin receptor-like neuroimmune suppression in atopic dermatitis.

The Journal of allergy and clinical immunology·2026

Same author

Multicenter ex vivo evaluation of an α-mannosidase-targeted fluorescent probe for intraoperative margin assessment in breast cancer.

Scientific reports·2026

Same author

Pembrolizumab for Early-Stage Triple-Negative Breast Cancer: KEYNOTE-522 Japan Subgroup Analysis.

Cancer science·2026

Same author

A novel quantification method for automatic computation of breast density from mammography images using deep learning.

Breast cancer (Tokyo, Japan)·2026

Same author

Cultural Adaptation and Preliminary Validation of Adherence Questionnaires for Japanese Patients with Breast Cancer: A Pilot Study.

Patient preference and adherence·2025

Same journal

[Multicenter Online Evaluation of IGRT Irradiation Position Accuracy Using an EPID-based End-to-end Postal Audit].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same journal

[Connecting Beyond Boundaries].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same journal

[The Forefront of Image Information Sharing between Medical Facilities].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same journal

[14. The Role of Radiological Technology Science in Targeted Radionuclide Therapy: Integrating Radiation Safety, Quantitative Imaging, and Dosimetry].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same journal

[Introduction of "JIRA Activity in 2026"].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

Same journal

[6. Data Literacy (4): Important Things to Keep in Mind When Analyzing Data].

Nihon Hoshasen Gijutsu Gakkai zasshi·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 16, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

[Automatic Quantification of Breast Density from Mammography Using Deep Learning].

Kenichi Inoue¹, Aika Kawasaki¹, Kanako Koshimizu¹

¹Shonan Memorial Hospital, Breast Cancer Center.

Nihon Hoshasen Gijutsu Gakkai Zasshi

|October 21, 2021

Summary

This summary is machine-generated.

A new deep learning system automatically quantifies breast density from mammograms, addressing the lack of objective breast density estimation in Japan. This automated system shows high consistency with human evaluations for dense breast identification.

Keywords:

breast screening deep learning dense breast semantic segmentation

More Related Videos

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

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

Published on: August 30, 2013

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

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

Published on: June 11, 2014

Related Experiment Videos

Last Updated: Oct 16, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

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

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

Published on: August 30, 2013

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

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

Published on: June 11, 2014

Area of Science:

Radiology and Medical Imaging
Artificial Intelligence in Healthcare
Biomedical Informatics

Background:

Objective breast density estimation is lacking in Japan's mammography screening.
This deficiency hinders accurate breast density classification for examinees.
Automated quantification of breast density is needed to improve screening objectivity.

Purpose of the Study:

To develop a deep learning system for automatic and objective breast density quantification.
To address the need for improved objectivity in breast density assessment.
To enhance the efficiency of mammography screening systems.

Main Methods:

Utilized mammography images diagnosed as category 1.
Developed a deep learning algorithm for semantic segmentation of breast tissue.
Calculated relative density by normalizing pixel values against fatty tissue.
Aggregated relative density to obtain an automated breast density score.

Main Results:

Successfully calculated breast density automatically for most mammograms.
Defined dense breast as a breast density score >= 30%.
Achieved 76.6% consistency in dense breast evaluation compared to computer and human assessments.

Conclusions:

Deep learning offers a highly effective method for quantifying breast density.
The developed system demonstrates potential to significantly improve mammography screening efficiency.
Automated breast density quantification enhances objectivity in breast cancer screening.