Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload
Journal of Breast Imaging · 22.05.2023 · 5 (3) · 267-276
DOI: 10.1093/jbi/wbad010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Breast Imaging, online erschienen am 31.03.2023. Verfasst von Annie Y Ng und 10 weiteren Autor:innen. Beteiligte Einrichtung: Kheiron Medical Technologies, London, UK. Hauptthemen laut MEDLINE: Artificial Intelligence, Breast Neoplasms. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council, Innovate UK.
Abstract (Originalsprache)
Objective
To evaluate the effectiveness of a new strategy for using artificial intelligence (AI) as supporting reader for the detection of breast cancer in mammography-based double reading screening practice.
Methods
Large-scale multi-site, multi-vendor data were used to retrospectively evaluate a new paradigm of AI-supported reading. Here, the AI served as the second reader only if it agrees with the recall/no-recall decision of the first human reader. Otherwise, a second human reader made an assessment followed by the standard clinical workflow. The data included 280 594 cases from 180 542 female participants screened for breast cancer at seven screening sites in two countries and using equipment from four hardware vendors. The statistical analysis included non-inferiority and superiority testing of cancer screening performance and evaluation of the reduction in workload, measured as arbitration rate and number of cases requiring second human reading.
Results
Artificial intelligence as a supporting reader was found to be superior or noninferior on all screening metrics compared with human double reading while reducing the number of cases requiring second human reading by up to 87% (245 395/280 594). Compared with AI as an independent reader, the number of cases referred to arbitration was reduced from 13% (35 199/280 594) to 2% (5056/280 594).
Conclusion
The simulation indicates that the proposed workflow retains screening performance of human double reading while substantially reducing the workload. Further research should study the impact on the second human reader because they would only assess cases in which the AI prediction and first human reader disagree.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Kheiron Medical Technologies, London, UK.
- Imperial College London, Department of Computing, London, UK.
- Leeds Teaching Hospital NHS Trust, Department of Radiology, Leeds, UK.
- Nottingham University Hospitals NHS Trust, Nottingham Breast Institute, Nottingham, UK.
- MaMMa Egészségügyi Zrt., Breast Diagnostic Department, Kecskemét, Hungary.
ORCID-Profile: Ben Glocker
Förderung
- Medical Research Council
- Innovate UK
Zitieren
APA
Ng, A. Y., Glocker, B., Oberije, C., Fox, G., Sharma, N., James, J. J., Ambrózay, É., Nash, J., Karpati, E., Kerruish, S., & Kecskemethy, P. D. (2023). Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload. Journal of Breast Imaging, 5(3), 267-276. https://doi.org/10.1093/jbi/wbad010
Vancouver
Ng AY, Glocker B, Oberije C, Fox G, Sharma N, James JJ, et al. Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload. Journal of Breast Imaging. 2023;5(3):267-276. doi:10.1093/jbi/wbad010
BibTeX
@article{Ng2023,
author = {Ng, Annie Y and Glocker, Ben and Oberije, Cary and Fox, Georgia and Sharma, Nisha and James, Jonathan J and Ambrózay, Éva and Nash, Jonathan and Karpati, Edith and Kerruish, Sarah and Kecskemethy, Peter D},
title = {Artificial Intelligence as Supporting Reader in Breast Screening: A Novel Workflow to Preserve Quality and Reduce Workload},
journal = {Journal of Breast Imaging},
year = {2023},
volume = {5},
number = {3},
pages = {267--276},
doi = {10.1093/jbi/wbad010}
}
EUVIMED