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

Artificial intelligence in food safety.

NPJ science of food·2026
Same author

A Community Benchmark for the Automated Segmentation of Pediatric Neuroblastoma on Multi-Modal MRI: Design and Results of the SPPIN Challenge at MICCAI 2023.

Bioengineering (Basel, Switzerland)·2025
Same author

Iodine Seed-Marking Protocol for Response-Guided Axillary Treatment After Systemic Therapy for Node-Positive Breast Cancer.

JAMA oncology·2025
Same author

Deep learning-based radiomics does not improve residual cancer burden prediction post-chemotherapy in LIMA breast MRI trial.

European radiology·2025
Same author

Evaluation of techniques for automated classification and artery quantification of the circle of Willis on TOF-MRA images: The CROWN challenge.

Medical image analysis·2025
Same author

Multireader Diagnostic Accuracy of Abbreviated Breast MRI for Screening Women with Extremely Dense Breasts.

Radiology·2025

Related Experiment Video

Updated: Dec 4, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

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

Published on: December 15, 2014

22.9K

Volumetric breast density estimation on MRI using explainable deep learning regression.

Bas H M van der Velden1, Markus H A Janse2, Max A A Ragusi2

  • 1Image Sciences Institute, University Medical Center Utrecht, Utrecht University, Q.02.4.45, P.O. Box 85500, 3508 GA, Utrecht, The Netherlands. bvelden2@umcutrecht.nl.

Scientific Reports
|October 23, 2020
PubMed
Summary
This summary is machine-generated.

This study demonstrates the feasibility of automatically estimating volumetric breast density from MRI scans using a convolutional neural network (CNN). The explainable AI approach accurately identifies breast tissue, improving diagnostic insights for breast cancer patients.

More Related Videos

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis
06:03

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Published on: February 6, 2020

6.9K
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

16.2K

Related Experiment Videos

Last Updated: Dec 4, 2025

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
15:48

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

Published on: December 15, 2014

22.9K
Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis
06:03

Integrating Augmented Reality Tools in Breast Cancer Related Lymphedema Prognostication and Diagnosis

Published on: February 6, 2020

6.9K
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

16.2K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background:

  • Accurate volumetric breast density estimation is crucial for breast cancer risk assessment and diagnosis.
  • Current methods often require manual segmentation, which is time-consuming and prone to inter-observer variability.
  • Magnetic Resonance Imaging (MRI) offers detailed tissue characterization but volumetric density estimation without segmentation remains challenging.

Purpose of the Study:

  • To assess the feasibility of volumetric breast density estimation on MRI without manual segmentation.
  • To incorporate an explainability step to understand the AI model's decision-making process.
  • To evaluate the accuracy and reliability of the automated estimation method.

Main Methods:

  • A 3-dimensional convolutional neural network (CNN) was developed for volumetric breast density estimation.
  • 615 breast cancer patients' MRI data were used, split into training, validation, and hold-out test sets.
  • SHapley Additive exPlanations (SHAP) were employed for visual analysis and model interpretability.

Main Results:

  • High correlation (Spearman's ρ = 0.81, P < 0.001) was observed between estimated and ground truth breast density in the test set.
  • The automated method showed a low median bias (0.70%) with acceptable limits of agreement (-6.8% to 5.0%).
  • SHAP analysis confirmed the model focused on fibroglandular and fatty tissues for accurate estimations, and identified extraneous structures in inaccurate ones.

Conclusions:

  • Automated volumetric breast density estimation on MRI without segmentation is feasible.
  • Integrating explainability (SHAP) enhances trust and understanding of the AI model's predictions.
  • This approach holds potential for improving efficiency and accuracy in breast density assessment for clinical applications.