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

The commercial artificial intelligence algorithm for breast cancer detection on screening mammograms performed well overall, but performance differed significantly based on breast density classification and presence or absence of architectural distortion or calcification.

Saved in:
Bibliographic Details
Published inRadiology. Artificial intelligence Vol. 7; no. 3; p. e240287
Main Authors Graham-Knight, John Brandon, Liang, Pengkun, Lin, Wenna, Wright, Quinn, Shen, Hua, Mar, Colin, Sam, Janette, Rajapakshe, Rasika
Format Journal Article
LanguageEnglish
Published United States 01.05.2025
Subjects
Aged
Algorithms
Artificial Intelligence
Breast - diagnostic imaging
Breast Neoplasms - diagnostic imaging
British Columbia
Early Detection of Cancer - methods
Female
Humans
Mammography - methods
Middle Aged
Radiographic Image Interpretation, Computer-Assisted - methods
Retrospective Studies
Sensitivity and Specificity
British Columbia
Screening
QA/QC
Technology Assessment
Artificial Intelligence
Bias and Fairness
Mammography
Model Testing
Screening Mammography
Breast Cancer
Online AccessGet full text
ISSN2638-6100
2638-6100
DOI10.1148/ryai.240287

Cover

More Information
Summary:The commercial artificial intelligence algorithm for breast cancer detection on screening mammograms performed well overall, but performance differed significantly based on breast density classification and presence or absence of architectural distortion or calcification.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2638-6100
2638-6100
DOI:10.1148/ryai.240287