Peer-Reviewed Publication
Radiol Med2026July 13, 2026Journal Article
Examining explainable artificial intelligence in TNM staging with PET-CT: a user-centred observation study.
Charlie Baskerville1,2, Julien M Y Willaime3, Vineet Prakash4,5,6, Tamir Ali7, Shaheel Bhuva8, Gordon Ellul9, Russell Frood10,11, Sachin Kamat12, Sudeshna Maitra5, David Rosewarne13, Andrew Scarsbrook10,11, Peter D Strouhal6, Amir Zarei10, Kevin Wells4
1Centre for Vision, Speech and Signal Processing, The University of Surrey, Guildford, UK. c.baskerville@surrey.ac.uk.
2Mirada Medical Ltd., Oxford, UK. c.baskerville@surrey.ac.uk.
3Mirada Medical Ltd., Oxford, UK.
4Centre for Vision, Speech and Signal Processing, The University of Surrey, Guildford, UK.
5Royal Surrey NHS Foundation Trust, Guildford, UK.
6Alliance Medical Ltd., Warwick, UK.
7The Newcastle Upon Tyne Hospitals NHS Foundation Trust, Newcastle Upon Tyne, UK.
8Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
9East Kent Hospitals University NHS Foundation Trust, Canterbury, UK.
10Leeds Teaching Hospitals NHS Trust, Leeds, UK.
11Faculty of Medicine and Health, University of Leeds, Leeds, UK.
12King's College London NHS Foundation Trust, London, UK.
13The Royal Wolverhampton NHS Trust, Wolverhampton, UK.
Abstract
PURPOSE: Artificial intelligence (AI) is increasingly proposed as a solution to improve efficiency in radiology and nuclear medicine, particularly in the context of workforce shortages. However, adoption of AI-based clinical decision support systems (AI-CDSS) remains slow, due to limited model transparency. Explainable AI (XAI) may improve clinician acceptance by supporting oversight and trust. Th…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans