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

Radiomics-based mammographic abnormality identification via radiologist annotations.

BJR artificial intelligence·2026
Same author

Tongluo Huoxue formula reduces ligamentum flavum fibrosis in lumbar spinal stenosis.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Stepwise nutritional management combined with multimodal rehabilitation for severe dysphagia following medullary infarction in an elderly patient: a case report.

Frontiers in nutrition·2026
Same author

Correction to: The role of digital rehabilitation therapy in enhancing upper limb function recovery following surgery in breast cancer patients.

Supportive care in cancer : official journal of the Multinational Association of Supportive Care in Cancer·2026
Same author

Nutrition-associated health levels in cancer patients based on the ICF: an expanded study of 300 cases.

Frontiers in nutrition·2026
Same author

Synergistic antibacterial mechanisms from kapok cellulose fiber structure and chemistry promote infected wound healing.

International journal of biological macromolecules·2026

Related Experiment Video

Updated: May 22, 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

42.6K

External Testing of a Commercial AI Algorithm for Breast Cancer Detection at Screening Mammography.

John Brandon Graham-Knight1, Pengkun Liang1, Wenna Lin1

  • 1Department of Medical Physics, BC Cancer-Kelowna, 399 Royal Ave, Kelowna, BC, Canada V1Y 5L3.

Radiology. Artificial Intelligence
|March 12, 2025
PubMed
Summary
This summary is machine-generated.

A commercial artificial intelligence (AI) system demonstrated generalizable breast cancer detection performance in a large Canadian screening cohort. However, AI performance varied across subgroups, notably with calcifications.

Keywords:
Artificial IntelligenceBias and FairnessBreast CancerMammographyModel TestingQA/QCScreeningScreening MammographyTechnology Assessment

More Related Videos

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

6.6K
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

22.3K

Related Experiment Videos

Last Updated: May 22, 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

42.6K
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

6.6K
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

22.3K

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence in Healthcare

Background:

  • Breast cancer screening programs aim for early detection.
  • Digital mammography is a standard screening tool.
  • Artificial intelligence (AI) is increasingly explored for medical image analysis.

Purpose of the Study:

  • To evaluate a commercial AI system's performance for breast cancer detection.
  • To assess AI generalizability in a large, external screening cohort.
  • To analyze AI performance variations across demographic, clinical, and imaging features.

Main Methods:

  • Retrospective analysis of 136,700 digital mammograms from British Columbia, Canada.
  • Evaluation of AI algorithm performance using Area Under the ROC Curve (AUC).
  • Comparison of AI sensitivity and specificity against radiologists.

Main Results:

  • The AI algorithm achieved an overall AUC of 0.93 for breast cancer detection.
  • AI performance varied significantly with breast density (AUC 0.84 for D vs. 0.96 for A).
  • AI showed higher performance with architectural distortion (0.96) but lower with calcifications (0.87).
  • Radiologist sensitivity (92.6%) initially exceeded AI (89.4%), with no difference at 2-year follow-up.

Conclusions:

  • The commercial AI system is generalizable for Canadian breast cancer screening.
  • AI performance is influenced by specific imaging features like calcifications and architectural distortion.
  • Further research is needed to optimize AI performance across diverse patient subgroups.