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

Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort.

Clinical and translational science·2026
Same author

Malignant vs. Non-malignant Annotations on TCGA Breast Cancer Whole Slide Images for AI Analysis.

Scientific data·2026
Same author

Clinicopathological characteristics of patients with inoperable non-small cell lung cancer harboring circulating NRF2 pathway mutations.

The Journal of pathology·2026
Same author

The role of digital twins in P4 medicine: A paradigm for modern healthcare.

NPJ digital medicine·2025
Same author

Threshold-Based Overlap of Breast Cancer High-Risk Classification Using Family History, Polygenic Risk Scores, and Traditional Risk Models in 180,398 Women.

Cancers·2025
Same author

GenoGraph: An Interpretable Graph Contrastive Learning Approach for Identifying Breast Cancer Risk Variants.

IEEE transactions on computational biology and bioinformatics·2025

Related Experiment Video

Updated: Sep 4, 2025

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

43.0K

Area-based breast percentage density estimation in mammograms using weight-adaptive multitask learning.

Naga Raju Gudhe1, Hamid Behravan2, Mazen Sudah3

  • 1Institute of Clinical Medicine, Pathology and Forensic Medicine, Multidisciplinary Cancer Research community, University of Eastern Finland, P.O. Box 1627, 70211, Kuopio, Finland. raju.gudhe@uef.fi.

Scientific Reports
|July 14, 2022
PubMed
Summary

A new deep learning model accurately estimates breast density from mammograms by simultaneously segmenting breast tissue and dense areas. This approach improves accuracy and reduces radiologist workload in breast cancer risk assessment.

More Related Videos

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

22.6K
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

6.7K

Related Experiment Videos

Last Updated: Sep 4, 2025

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

43.0K
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

22.6K
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

6.7K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Biomedical Engineering

Background:

  • Breast density is a key breast cancer risk factor, necessitating accurate measurement from mammograms.
  • Current computer-aided tools for breast density estimation have limitations in accuracy, view specificity, and handling data variability.
  • Accurate segmentation of fibroglandular tissue and the breast area is essential for reliable breast density computation.

Purpose of the Study:

  • To develop a novel deep learning architecture for automated breast percentage density estimation from mammograms.
  • To simultaneously segment the breast area, dense tissues, and estimate breast percentage density.
  • To improve upon existing methods' limitations in accuracy and handling diverse mammographic data.

Main Methods:

  • Proposed a weight-adaptive multitask learning deep learning architecture.
  • The model performs simultaneous segmentation of breast and dense tissues.
  • Evaluated on 7500 mammograms (craniocaudal and mediolateral oblique views) from Kuopio University Hospital.

Main Results:

  • The proposed multitask segmentation approach achieved superior performance compared to multitask U-net and fully convolutional neural networks.
  • Demonstrated average relative improvements of 2.88% (vs. U-net) and 9.78% (vs. FCN) in F-score for segmentation.
  • Estimated breast density values showed strong correlation with radiologists' assessments (Pearson's correlation of [Formula: see text]).

Conclusions:

  • The developed deep learning approach significantly enhances segmentation accuracy for breast area and dense tissues.
  • The model plays a vital role in accurately computing breast percentage density.
  • This automated method reduces radiologist time and effort, decreasing inter- and intra-reader variability in density estimation.