Lessons learned from independent external validation of an AI tool to detect breast cancer using a representative UK data set
The British Journal of Radiology · 2023
DOI: 10.1259/bjr.20211104 ↗Kurz gefasst
Fachartikel in der Zeitschrift The British Journal of Radiology, 2023. Verfasst von Dominic Cushnan und 13 weiteren Autor:innen. Beteiligte Einrichtung: AI Lab, NHSX, Skipton House, London, United Kingdom. Hauptthemen laut MEDLINE: Breast Neoplasms. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 9 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Cancer Research UK.
Abstract (Originalsprache)
Objective
To pilot a process for the independent external validation of an artificial intelligence (AI) tool to detect breast cancer using data from the NHS breast screening programme (NHSBSP).
Methods
A representative data set of mammography images from 26,000 women attending 2 NHS screening centres, and an enriched data set of 2054 positive cases were used from the OPTIMAM image database. The use case of the AI tool was the replacement of the first or second human reader. The performance of the AI tool was compared to that of human readers in the NHSBSP.
Results
Recommendations for future external validations of AI tools to detect breast cancer are provided. The tool recalled different breast cancers to the human readers. This study showed the importance of testing AI tools on all types of cases (including non-standard) and the clarity of any warning messages. The acceptable difference in sensitivity and specificity between the AI tool and human readers should be determined. Any information vital for the clinical application should be a required output for the AI tool. It is recommended that the interaction of radiologists with the AI tool, and the effect of the AI tool on arbitration be investigated prior to clinical use.
Conclusion
This pilot demonstrated several lessons for future independent external validation of AI tools for breast cancer detection. Advances in knowledge Knowledge has been gained towards best practice procedures for performing independent external validations of AI tools for the detection of breast cancer using data from the NHS Breast Screening Programme.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- AI Lab, NHSX, Skipton House, London, United Kingdom.
- Royal Surrey NHS Foundation Trust, Guildford, United Kingdom.
- University of Surrey, Guildford, United Kingdom.
- Queen Mary University London, London, United Kingdom.
- St George's Healthcare NHS Trust, Tooting, London, United Kingdom.
- Cambridge Breast Unit and NIHR Cambridge Biomedical Research Centre, Cambridge University Hospitals NHS Trust, Cambridge, United Kingdom.
Förderung
- Cancer Research UK
Zitieren
APA
Cushnan, D., Young, K. C., Ward, D., Halling-Brown, M. D., Duffy, S., Given-Wilson, R., Wallis, M. G., Wilkinson, L., Lyburn, I., Sidebottom, R., McAvinchey, R., Lewis, E. B., Mackenzie, A., & Warren, L. M. (2023). Lessons learned from independent external validation of an AI tool to detect breast cancer using a representative UK data set. The British Journal of Radiology. https://doi.org/10.1259/bjr.20211104
Vancouver
Cushnan D, Young KC, Ward D, Halling-Brown MD, Duffy S, Given-Wilson R, et al. Lessons learned from independent external validation of an AI tool to detect breast cancer using a representative UK data set. The British Journal of Radiology. 2023. doi:10.1259/bjr.20211104
BibTeX
@article{Cushnan2023,
author = {Cushnan, Dominic and Young, Kenneth C and Ward, Dominic and Halling-Brown, Mark D and Duffy, Stephen and Given-Wilson, Rosalind and Wallis, Matthew G and Wilkinson, Louise and Lyburn, Iain and Sidebottom, Richard and McAvinchey, Rita and Lewis, Emma B and Mackenzie, Alistair and Warren, Lucy M},
title = {Lessons learned from independent external validation of an AI tool to detect breast cancer using a representative UK data set},
journal = {The British Journal of Radiology},
year = {2023},
doi = {10.1259/bjr.20211104}
}
EUVIMED