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

2025 Update of the Taiwan Expert Consensus on Hormone Receptor-Positive Metastatic Breast Cancer Management.

Journal of breast cancer·2026
Same author

Reassessing the risk-modifying effects of novel antidiabetic agents on asthma-COPD overlap syndrome: a dose-stratified network meta-analysis of 316,832 adults from 128 randomised trials.

EClinicalMedicine·2026
Same author

Integrative Transcriptomic and Proteomic Profiling Identifies S100P as a Potential Functional Biomarker for Sessile Serrated Lesions.

Digestive diseases and sciences·2026
Same author

Differential Acute Kidney Injury Profiles of GLP-1RAs and SGLT2is: A Network Meta-Analysis.

International journal of molecular sciences·2026
Same author

Agent-specific, histopathology-stratified hematologic malignancy risk among dpp-4 inhibitors, glp-1 receptor agonists, and SGLT2 inhibitors: a network meta-analysis of 270,471 participants.

Journal of hematology & oncology·2026
Same author

Gastric Neoplasm Risk with DPP-4 Inhibitors, GLP-1 Receptor Agonists, and SGLT2 Inhibitors: Network Meta-Analysis of Randomized Trials.

International journal of molecular sciences·2026

Related Experiment Video

Updated: Oct 3, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography.

Kuen-Jang Tsai1,2, Mei-Chun Chou3, Hao-Ming Li3

  • 1Department of General Surgey, E-Da Cancer Hospital, Yanchao Dist., Kaohsiung 82445, Taiwan.

Sensors (Basel, Switzerland)
|February 15, 2022
PubMed
Summary
This summary is machine-generated.

A novel deep neural network (DNN) model assists radiologists in interpreting mammograms by classifying them into all BI-RADS categories. This AI tool achieved high accuracy, improving early breast cancer detection efficiency.

Keywords:
breast imaging reporting and data system (BI-RADS)deep learningdeep neural network (DNN)image classificationscreening mammography

More Related Videos

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

43.1K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Related Experiment Videos

Last Updated: Oct 3, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K
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

43.1K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.0K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Oncology and Radiology
  • Machine Learning for Breast Cancer Screening

Background:

  • Breast cancer is the leading global cancer incidence, with early-stage treatment being cost-effective and achieving high survival rates.
  • Screening mammography is crucial for early breast cancer detection, leading to increased radiologist workload.
  • Taiwan's national screening program targets women aged 45-69 for biennial mammograms.

Purpose of the Study:

  • To develop an efficient and reliable deep neural network (DNN)-based model to aid radiologists in mammographic interpretation.
  • To classify mammograms into all Breast Imaging Reporting and Data System (BI-RADS) categories (0-5) for comprehensive analysis.
  • To enhance the accuracy and efficiency of breast cancer screening, particularly for populations with dense breasts.

Main Methods:

  • A deep neural network (DNN) model was developed and trained using segmented block-based images from a proprietary mammogram dataset.
  • Each block-based image served as input, with the model predicting a corresponding BI-RADS category as output.
  • The model was specifically trained on mammograms from Taiwanese women, considering their higher likelihood of dense breasts.

Main Results:

  • The DNN model demonstrated superior performance with an overall accuracy of 94.22%.
  • High average sensitivity (95.31%) and specificity (99.15%) were achieved, indicating reliable detection and classification.
  • An area under the curve (AUC) of 0.9723 signifies excellent model discriminative ability.

Conclusions:

  • The proposed DNN-based model offers an efficient and accurate tool for mammographic interpretation, assisting radiologists.
  • This model's comprehensive classification across all BI-RADS categories represents a novel contribution to breast cancer diagnostics.
  • The model is expected to yield higher accuracy in breast cancer screening for Asian women with dense breasts compared to existing methods.