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 authorSame journal

Automation Bias in Action: Eye Tracking of Humans Reading Screening Mammograms with and without AI Prompts.

Radiology·2026
Same author

Artificial Intelligence for Digital Breast Tomosynthesis Screening with and without Prior Examinations in BreastScreen Norway.

Radiology. Artificial intelligence·2026
Same author

Open-Source Dataset for the RSNA Screening Mammography Cancer Detection Challenge.

Radiology. Artificial intelligence·2026
Same author

Tumor Involvement of the Nipple at Preoperative Contrast-enhanced Mammography: A Multicenter Diagnostic Accuracy Study.

Radiology·2025
Same author

Performance of Algorithms Submitted in the 2023 RSNA Screening Mammography Breast Cancer Detection AI Challenge.

Radiology·2025
Same author

Variation within and between digital pathology and light microscopy for the diagnosis of histopathology slides: blinded crossover comparison study.

Health technology assessment (Winchester, England)·2025

Related Experiment Video

Updated: Jul 17, 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

42.9K

Performance of a Breast Cancer Detection AI Algorithm Using the Personal Performance in Mammographic Screening

Yan Chen1, Adnan G Taib1, Iain T Darker1

  • 1From the Department of Translational Medical Sciences, School of Medicine, University of Nottingham, Clinical Sciences Building, Nottingham City Hospital, City Hospital Campus, Hucknall Rd, Nottingham NG5 1PB, United Kingdom (Y.C., A.G.T., I.T.D.); and Nottingham Breast Institute, Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom (J.J.J.).

Radiology
|September 5, 2023
PubMed
Summary

Artificial intelligence (AI) demonstrated comparable diagnostic performance to human readers in mammographic screening using the Personal Performance in Mammographic Screening (PERFORMS) scheme. AI showed higher specificity, suggesting potential for improved screening accuracy.

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

6.8K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

74

Related Experiment Videos

Last Updated: Jul 17, 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

42.9K
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

6.8K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

74

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • The Personal Performance in Mammographic Screening (PERFORMS) scheme assesses human reader performance.
  • Its utility in evaluating artificial intelligence (AI) algorithms for mammography is not established.

Purpose of the Study:

  • To compare the diagnostic performance of a commercial AI algorithm against human readers using PERFORMS test sets.
  • To determine if AI can be assessed using the PERFORMS scheme.

Main Methods:

  • Retrospective analysis of two PERFORMS test sets (60 challenging cases each).
  • AI algorithm evaluated cases, assigning malignancy suspicion scores.
  • Performance metrics (sensitivity, specificity, AUC) calculated for AI and 552 human readers.

Main Results:

  • No significant difference in Area Under the Curve (AUC) between AI (0.93) and human readers (0.88).
  • AI specificity (89%) was higher than human readers (76%) at the developer's suggested threshold.
  • AI performance was comparable to average human performance when matched for sensitivity and specificity.

Conclusions:

  • AI diagnostic performance is comparable to average human readers in interpreting challenging mammographic screening cases.
  • The PERFORMS scheme can be utilized to assess AI performance in mammography.
  • AI may offer improved specificity in mammographic interpretation.