ESTRO 2025 - Abstract Book

S3437

Physics - Machine learning models and clinical applications

ESTRO 2025

Conclusion: Results suggest that this framework combining ML and MC simulations can provide insight into the biological effects of heavy particle irradiation. This model is versatile, and given the small number of features used, it's very easy to use in an experimental setting, offering a robust alternative to other models.

Keywords: Cell survival, Machine learning, Monte Carlo

References: [1] Friedrich, T., Pfuhl, T., Scholz, M., Update of the particle irradiation data ensemble (PIDE) for cell survival, Journal of Radiation Research, Volume 62, Issue 4, July 2021, Pages 645 – 655 [2] Battistoni, G., Boehlen, T., Cerutti, F., et al. (2015). Overview of the fluka code. Annals of Nuclear Energy,82:10 – 18. [3] Salgado , S., Carabe A., Espinoza I., et al. (2023). Monte Carlo simulations of cell survival in proton SOBP. Physics in Medicine & Biology 68.19: 195024. [4] Wouters B. G., Skarsgard L.D., Gerweck L.E., et al (2015). Radiobiological intercomparison of the 160 MeV and 230 MeV proton therapy beams at the harvard cyclotron laboratory and at massachusetts general hospital Radiat. Res. 183 174.

3864

Digital Poster Decoding AI-adoption in radiotherapy: A multi-case qualitative comparative analysis

Martijn Vroegindeweij 1,2 , Luca Heising 2,1 , Carol X.J. Ou 1 , Wouter van Elmpt 2 , Maria Jacobs 2,3 1 Information systems & Operations management, Tilburg University, Tilburg, Netherlands. 2 Innovation Research, Maastro, Maastricht, Netherlands. 3 Strategy and Entrepreneurship, Tilburg University, Tilburg, Netherlands Purpose/Objective: Over the past decade, Artificial Intelligence (AI) has gained significant attention in radiotherapy (RT) research. Nevertheless, in clinical practice, the number of implemented AI applications remains limited. The most prevailing AI tools are organ at risk (OAR) auto-contouring, followed by auto-planning. This study aims to identify and decode the patterns of conditions that facilitate the adoption of AI in radiotherapy using Qualitative Comparative Analysis (QCA). Material/Methods: A multi-case analysis was conducted across eight radiotherapy centers in the Netherlands. Eighteen interviews were held with clinicians, medical physicists, and radiotherapy technologists. The study employed QCA to quantify qualitative data and identify patterns across cases. Key variables examined included data set characteristics, IT capabilities, AI configurability, explainable AI, stakeholder involvement, and standardization of contouring guidelines. Results: Auto-contouring was frequently mentioned as a successful implementation (5 out of 8 centers), and a couple of centers also adopted auto-planning (2 out of 8 centers). Twelve interviewees questioned the effectiveness of AI, acknowledging that while it saves radiotherapists time, it doesn't fully automate the workflow, and human oversight is still necessary as the model can be inaccurate. The QCA revealed multiple pathways leading to successful AI adoption. Crucially, the presence of AI configurability and stakeholder involvement emerged as consistent factors in positive outcomes. Centers that lacked high-quality data set characteristics faced significant barriers, as insufficient or non-standardized data led to inaccurate AI performance. Conversely, when centers had data sets with standardized contouring guidelines, auto-contouring performed more effectively.