Systematic prioritisation of AI-detected chest X-ray abnormalities for optimised lung cancer detection
BJR|Artificial Intelligence · 23.01.2026 · 3 (1)
DOI: 10.1093/bjrai/ubag007 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift BJR|Artificial Intelligence, online erschienen am 26.03.2026. Verfasst von Rhidian R Bramley und 7 weiteren Autor:innen. Beteiligte Einrichtung: Greater Manchester Cancer Alliance, c/o The Christie NHS Foundation Trust, Manchester, M20 4BX, United Kingdom. Die Arbeit nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHS England Artificial Intelligence Diagnostic Fund.
Abstract (Originalsprache)
This paper presents a reproducible, data-driven approach for prioritisation of AI-detected chest X-ray (CXR) findings to support faster lung cancer diagnosis in the NHS. The Annalise Enterprise CXR system was deployed in shadow mode across seven acute trusts in Greater Manchester. Two cohorts were used: a retrospective cancer cohort (n = 1,282) with confirmed lung cancer and visible CXR abnormalities, and a prospective cohort (n = 13,802) comprising consecutively acquired GP-referred CXRs. Prevalence ratios were calculated for 124 AI-detected abnormalities across both cohorts, and three prioritisation strategies were developed. Strategy 3, which combined prevalence analysis with expert clinical review, achieved optimal performance with a sensitivity of 95.87% and estimated specificity of 79.11%, while maintaining a negative predictive value of 99.95%, for identification of lung cancer. Findings most associated with cancer included solitary lung mass, mediastinal mass, and hilar lymphadenopathy. An Excel-based tool was developed to support rapid configuration and evaluation of categorisation. Application of this approach enabled safe deployment of AI using shadow mode to inform configuration prior to live use. This work provides a scalable model for AI implementation in radiology workflows that aligns with the National Optimal Lung Cancer Pathway and addresses real-world challenges of diagnostic capacity, safety, and reproducibility.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Greater Manchester Cancer Alliance, c/o The Christie NHS Foundation Trust, Manchester, M20 4BX, United Kingdom.
- Department of Radiology, Manchester University NHS Foundation Trust, Oxford Road, Manchester, M13 9WL, United Kingdom.
- Department of Radiology, Stockport NHS Foundation Trust, Stepping Hill Hospital, Poplar Grove, Stockport, SK2 7JE, United Kingdom.
- Annalise.ai , 301/100 Harris Street, Pyrmont, NSW, 2009, Australia.
- Sectra Imaging IT Solutions, Teknikringen 20, SE-583 30, Linköping, Sweden.
- Lung Cancer & Thoracic Surgery Directorate, Wythenshawe Hospital, Manchester University NHS Foundation Trust, Manchester, M13 9WL, United Kingdom.
ORCID-Profile: Rhidian R Bramley, Anna C Sharman, Rebecca Duerden, Melissa Ryan, Elodie Weber, Louise Brown
Förderung
- NHS England Artificial Intelligence Diagnostic Fund
Zitieren
APA
Bramley, R. R., Sharman, A. C., Duerden, R., Lyon, S., Ryan, M., Weber, E., Brown, L., & Evison, M. (2026). Systematic prioritisation of AI-detected chest X-ray abnormalities for optimised lung cancer detection. BJR|Artificial Intelligence, 3(1). https://doi.org/10.1093/bjrai/ubag007
Vancouver
Bramley RR, Sharman AC, Duerden R, Lyon S, Ryan M, Weber E, et al. Systematic prioritisation of AI-detected chest X-ray abnormalities for optimised lung cancer detection. BJR|Artificial Intelligence. 2026;3(1). doi:10.1093/bjrai/ubag007
BibTeX
@article{Bramley2026,
author = {Bramley, Rhidian R and Sharman, Anna C and Duerden, Rebecca and Lyon, Sarah and Ryan, Melissa and Weber, Elodie and Brown, Louise and Evison, Matthew},
title = {Systematic prioritisation of AI-detected chest X-ray abnormalities for optimised lung cancer detection},
journal = {BJR|Artificial Intelligence},
year = {2026},
volume = {3},
number = {1},
doi = {10.1093/bjrai/ubag007}
}
EUVIMED