Keeping AI on Track: Regular monitoring of algorithmic updates in mammography.

Journal: European journal of radiology

PMID: 40252280

Abstract

PURPOSE: To demonstrate a method of benchmarking the performance of two consecutive software releases of the same commercial artificial intelligence (AI) product to trained human readers using the Personal Performance in Mammographic Screening scheme (PERFORMS) external quality assurance scheme.

Authors

Adnan G Taib

Translational Medical Sciences, School of Medicine, University of Nottingham, Clinical Sciences Building, Nottingham City Hospital, Nottingham NG5 1PB, United Kingdom.
Jonathan J James

Nottingham University Hospitals NHS Trust, Nottingham Breast Institute, Nottingham, UK.
George J W Partridge

Translational Medical Sciences, School of Medicine, University of Nottingham, Clinical Sciences Building, Nottingham City Hospital, Nottingham NG5 1PB, United Kingdom.
Yan Chen

Department of Respiratory and Critical Care Medicine, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China.

Keywords

Algorithms Artificial Intelligence Benchmarking Breast Neoplasms Female Humans Mammography Middle Aged Radiographic Image Interpretation, Computer-Assisted Reproducibility of Results Retrospective Studies Sensitivity and Specificity

External Resources

View on PubMed Access via DOI PubMed (40252280)

Keeping AI on Track: Regular monitoring of algorithmic updates in mammography.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals