ESTRO 2022 - Abstract Book

S1647

Abstract book

ESTRO 2022

is to be hoped that DWI-MRI and IVIM-MRI techniques, which are so promising in the MRI approach, will contribute more and more to diagnostic improvement, both in the field of research and clinics.

PO-1856 Artificial intelligence: the opinions of radiation therapists in Ireland.

T. O' Donovan 1 , J. McNulty 2 , M. Ryan 2

1 University College Cork, School of Medicine, Cork, Ireland; 2 University College Dublin, School of Medicine, Dublin, Ireland

Purpose or Objective A new era has dawned for radiation therapists (RTTs). Having adapted to substantial changes throughout their professional history, perhaps the most significant change is now imminent. Artificial Intelligence (AI) is set to change relationships between humans and their work, with some roles disappearing and new ones created. The implementation of Artificial Intelligence (AI) into radiation therapy is much debated. Radiation Therapists (RTTs) are at the forefront of this technological leap, thus an understanding of their views, in particular changes to their current roles, is key to safe and optimal implementation. Materials and Methods A 34-item survey was developed through an in-depth literature review to ascertain quantitative and qualitative data. The survey was in seven sections: demographic data; RTT current knowledge in AI; AI applications currently in clinical use and areas for priority development; the potential impact of the RTT role; patient impact due to AI; development, regulation, testing, and ethical considerations; AI education; future perspectives. The study adhered to the ethical requirements of the researcher’s university ethics committee. The survey population was Irish RTTs. It was distributed via the Irish professional body, through services managers nationally, and the online software Survey Monkey. Open and closed- ended ended questions were used to elicit the information. For data analysis, descriptive statistics were employed to describe the results of closed questions. Open questions were coded in a thematic manner discovering patterns and developing themes, to achieve a deeper understanding of the data. Results 77/476 (16.2%) registered RTTs participated. Priority areas for development included treatment planning algorithm optimisation, clinical audit, and post-processing. There was resistance regarding AI use for patient-facing roles and final image interpretation. 40.3% of RTTs currently use AI clinically and 41.2% of RTTs anticipate reduced staffing levels with AI. 70.6% of RTTs felt AI will be positive for patients, with the majority promoting AI regulation through national legislation. 94.0% of RTTs were favourable to AI implementation. Conclusion Understanding opinions on AI has significant implications for education and training, ensuring optimal product development and implementation, together with planning for RTT role development in practice. This research identifies priority AI development and implementation areas for RTTs. It thus highlights that RTTs should be involved in development of AI tools that would best support practice, and that clearly defined pathways for AI implementation into this key profession requires discussion so that optimum use and patient safety can ensue. 1 Edinburgh Cancer Centre, Department of Therapeutic Radiography, Edinburgh, United Kingdom; 2 Edinburgh Cancer Centre, Department of Clinical Oncology, Edinburgh, United Kingdom Purpose or Objective Intra-fraction motion remains an important consideration in stereotactic body irradiation (SBRT) for prostate cancer because of the risk of serious adverse effects. With 10-year mortality less than 5% for low- and intermediate-risk patients, and a significant increase in the use of SBRT, robust techniques for reducing these effects are required. The aim of this study was to assess the potential of the RayPilot ® real-time motion management system for monitoring intra-fraction motion and consequently for margin reduction, which would lead to reduced side-effects. Materials and Methods Radiotherapy planning computed tomography (CT) images, treatment plans and cone beam CT (CBCT) images were collected at each fraction (N=5) of SBRT (36.25 Gy in 5 fractions) treatment for low- (N=7) to intermediate-risk (N=4) prostate cancer patients (Table 1). Inter-fraction motion displacements in the lateral, longitudinal and vertical planes were recorded every second by the RayPilot® system and used as input to the van Herk margin formula (VHMF) to establish a set of new planning target margins. All patients were replanned on the Varian Eclipse treatment planning system (TPS) using the original fractionation schedule and a new schedule (24 Gy in 3 fractions) based on the new margins. Dose coverage was assessed for the clinical target volume (CTV), rectum and bladder. Results Using this approach the planning margins were reduced from 1.0 cm to 0.67 cm in the lateral, 1.0cm to 0.67 cm in the longitudinal and 0.8 cm to 0.67 cm in the vertical directions, which were found to provide adequately dosimetric coverage of the CTV whilst accounting for inter- and intra-fraction motion on each patient. In addition there was a mean reduction PO-1857 A feasibility study on RayPilot® real-time motion management for margin reduction in prostate SBRT. S. Adamson 1,2 , D. McLaren 2 , W. Nailon 2