The use of Artificial Intelligence to detect incidental/additional findings on plain, projection-based radiographs of the chest

   Faculty of Health and Life Sciences

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Prof Ciara Hughes  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

AI is increasingly being integrated into the clinical setting, with impressive accuracies noted across many modalities, including plain radiography. Chest x-rays are a commonly conducted, first line investigation in patients presenting with symptoms which may indicate cancer (and/or other conditions), however, 90% of undetected lung cancers are missed by clinicians on initial chest x-rays, meaning that these patients may not be sent for further investigation and/or treatment.

AI has been proposed as a way to increase accuracy and decrease error, whilst allowing for time efficiencies for clinicians. No study has determined the use of AI for detection of additional (incidental findings) on any imaging modality. This study aims to discover if AI applied to a retrospective sample of images will detect additional findings, not reported at the time of the initial radiological report. Patient and clinician perspectives of the use of the technology for this purpose will be investigated. Clinical outcome of the patients/service users will be investigated and the relevance of any additional findings on eventual diagnoses and/or clinical outcome will be determined.

Aim: to determine if a commercially available AI model, trained to provide diagnosis on plain chest radiographs, can detect additional pathology not detected at initial report and determine the potential clinical impact of any additional findings.


To gain public/service user and clinician perception on the detection of incidental findings from imaging studies

To determine if a CE approved AI model can detect additional findings on chest radiographs, not detected at initial report.

To investigate the prevalence and nature of any additional findings and their clinical relevance

To follow to patient journey to determine their health outcomes

Medicine (26) Nursing & Health (27)


Cyphers, E., Krishnasamy , V., & Weintraub, J. (2023). AI and Incidental Findings: A Retrospective Duty? . Voices in Bioethics, 9.
Davenport MS. Incidental Findings and Low-Value Care. AJR Am J Roentgenol. 2023 Jul;221(1):117-123. doi: 10.2214/AJR.22.28926. Epub 2023 Jan 11. PMID: 36629303
Zhang et al., 2023 Zhang, L., Wen, X., Li, J. W., Jiang, X., Yang, X. F., & Li, M. (2023) Diagnostic error and bias in the department of radiology: a pictorial essay. Insights into imaging, 14(1), 163.
Kim YW, Mansfield LT. Fool me twice: delayed diagnoses in radiology with emphasis on perpetuated errors. AJR Am J Roentgenol. 2014;202:465–470. doi: 10.2214/AJR.13.11493
Park, G. E., Kang, B. J., Kim, S. H., & Lee, J. (2022). Retrospective Review of Missed Cancer Detection and Its Mammography Findings with Artificial-Intelligence-Based, Computer-Aided Diagnosis. Diagnostics (Basel, Switzerland), 12(2), 387
RCR (2020) Clinical radiology UK workforce census 2019 report. Available at:
The College of Radiographers (2020) CoR Diagnostic Radiography Workforce Census 2020. Available at:
Mehrizi MH, van Ooijen P, Homan M. (2020) Applications of artificial intelligence (AI) in diagnostic radiology: a technography study. European Radiology. 31(4) pp.1805-1811. .
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

 About the Project