ESTRO 2025 - Abstract Book

S2308

Interdisciplinary – Health economics & health services research

ESTRO 2025

Conclusion: Gantry-less radiotherapy with upright patient positioning holds significant promise, particularly for enhancing radiotherapy accessibility and enabling the development of innovative RT technologies. The workshop participants reached a consensus on the current challenges and technological opportunities associated with new workflows in upright radiotherapy. However, significant work remains. Realizing the potential of gantry-less treatments in the coming years will require continued collaborative efforts from academia, hospitals, and industry, ideally supported by patient representatives

Keywords: image guidance; radiotherapy; upright positioning

References: [1] Volz L, Korte J, Martire MC, Zhang Y, Hardcastle N, Durante M, Kron T, Graeff C. Opportunities and challenges of upright patient positioning in radiotherapy. Phys Med Biol. 2024 Sep 12;69(18). doi: 10.1088/1361-6560/ad70ee

2688

Proffered Paper Results from a multi-centre, multi-vendor real-world health economic evaluation of AI auto-contouring tools in the NHS Catriona Inverarity 1 , Benjamin Caswell-Midwinter 1 , Babak Jamshidi 1 , Emily Kwong 2 , Chloe Black 2 , Juan I Baeza 3 , Jon Hindmarsh 3 , Alison Griffiths 1 , Angie A Kehagia 1 , Anna Barnes 1,2 1 King's Technology Evaluation Centre, King's College London, London, United Kingdom. 2 Department of Medical Physics, Guy's and St Thomas' NHS Foundation Trust, London, United Kingdom. 3 King's Business School, King's College London, London, United Kingdom Purpose/Objective: Artificial intelligence (AI) is widely used across NHS radiotherapy departments in contouring organs-at-risk (OARs), but there is little multi-centre evidence to robustly evaluate its benefit. This real-world, multi-vendor evaluation compared the use of AI auto-contouring tools with manual contouring of OARs on resource use, time spent across the treatment planning pathway and clinical acceptability. Material/Methods: Data for 626 CT images for primary tumours of the breast, head and neck, prostate and lung were collected from 8 radiotherapy departments in NHS England. This included time of activities on the treatment pathway, role of the professional performing each task, and acceptability of the AI-generated contour (rated 0-3) 1 . Contour and reviewing time per staff type informed the cost comparison based on the NICE template 2 . A concurrent qualitative study explored experiences of staff working with the AI tools regarding workforce and workflow impact. Background information on staff and equipment resourcing, local pathways and patient throughput was also collected. Results: AI auto-contouring reduced contouring time for all primary tumour sites. These time savings were not translated across the treatment pathway, which was principally informed by NHS waiting time standards.