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

Empirical Comparison of Win Ratio and Joint Frailty Models for Recurrent Event Endpoints With Applications in Oncology and Cardiology.

Statistics in medicine·2026
Same author

Two Doppler blood pressure devices and 2 oscillometric blood pressure devices failed American College of Veterinary Internal Medicine validation in conscious dogs.

American journal of veterinary research·2026
Same author

Mediation Analysis With Bayesian Nonlinear Joint Models: Evaluation of the Treatment Causal Pathways Between Tumor Growth Kinetics and Overall Survival.

Statistics in medicine·2026
Same author

Impact of the French ENDOCAN-COMETE Network on Overall Survival in Rare Adrenocortical Carcinomas.

Journal of the National Comprehensive Cancer Network : JNCCN·2026
Same author

Dual-modality CAD for breast cancer screening: dealing with discordant diagnosis between mammography and tomography.

Frontiers in oncology·2026
Same author

Retrospective Evaluation of Treatment of Coagulopathy Secondary to Suspected Vitamin K Antagonist Rodenticide Intoxication With Cryosupernatant Transfusion in Seven Dogs (2000-2017).

Journal of veterinary emergency and critical care (San Antonio, Tex. : 2001)·2026

Related Experiment Video

Updated: Apr 26, 2026

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

25.0K

The DeepJoint Algorithm: An Innovative Approach for Studying the Longitudinal Evolution of Quantitative Mammographic

Manel Rakez1, Julien Guillaumin2, Aurelien Chick2

  • 1BIOSTAT Team, Bordeaux Population Health, U1219, ISPED, Bordeaux, France.

Biometrical Journal. Biometrische Zeitschrift
|April 25, 2026
PubMed
Summary

DeepJoint integrates deep learning with joint modeling to analyze longitudinal mammographic density changes, improving breast cancer risk prediction. This method offers a robust framework for personalized risk assessment using mammograms from diverse sources.

Keywords:
breast cancer screeningdeep learning modeldynamic risk predictionjoint modelmammographic density

More Related Videos

Changes in Mammary Gland Morphology and Breast Cancer Risk in Rats
09:36

Changes in Mammary Gland Morphology and Breast Cancer Risk in Rats

Published on: October 16, 2010

30.9K
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

42.6K

Related Experiment Videos

Last Updated: Apr 26, 2026

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

25.0K
Changes in Mammary Gland Morphology and Breast Cancer Risk in Rats
09:36

Changes in Mammary Gland Morphology and Breast Cancer Risk in Rats

Published on: October 16, 2010

30.9K
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

42.6K

Area of Science:

  • Biomedical Imaging
  • Machine Learning
  • Epidemiology

Background:

  • High mammographic density is a significant breast cancer risk factor.
  • Current automated methods often analyze density cross-sectionally, ignoring longitudinal data.
  • Existing methods overlook correlations in repeated measures, irregular visits, and missing data.

Purpose of the Study:

  • To introduce DeepJoint, an open-source algorithm for estimating mammographic density longitudinally.
  • To assess the relationship between longitudinal mammographic density and breast cancer risk.
  • To provide individualized breast cancer risk predictions using a comprehensive framework.

Main Methods:

  • Combined deep learning for mammographic density estimation (dense area, percent density) with joint modeling.
  • Utilized Bayesian inference and consensus Monte Carlo for reliable analysis of large datasets.
  • Developed an open-source pipeline for processing mammograms from various manufacturers.

Main Results:

  • The DeepJoint algorithm effectively estimates mammographic density from diverse sources.
  • Established the longitudinal association between mammographic density metrics and breast cancer risk.
  • Enabled individualized risk predictions based on temporal density changes.

Conclusions:

  • Deep learning integrated with joint modeling offers a robust framework for breast cancer risk evaluation.
  • The DeepJoint algorithm addresses limitations of cross-sectional density assessments.
  • The open-source availability promotes wider adoption and validation of the method.