ESTRO 2025 - Abstract Book

S2170

Interdisciplinary – Education in radiation oncology

ESTRO 2025

Conclusion: Our review highlights that human actions and machine functions do not occur in isolation. Just as the interaction between pilots and machines has been a source of many aviation accidents, the handover between clinical specialists and automated systems in radiation oncology presents similar risks. Understanding and acknowledging human factors when balancing automation with human involvement is crucial. This underscores the value of using generalised language, as presented by Callens et al(1), and highlights the importance of learning from other professions. References: 1. Callens D et al. (2024). Is full-automation in radiotherapy ready for take off? Radiother Oncol; 201:110546 2. Cardenas CE et al. (2019). Advances in auto segmentation. Semin Radiat Oncol; 29(3):185-197 3. Sarria GR et al. (2024). AI-based autosegmentation advantages. Adv Radiat Oncol; 9(3):101394 4. Landry G et al. (2023). Role of AI in radiotherapy practice. BJR Open; 5(1):20230030 5. Mahdavi SR et al. (2019). ANN for pretreatment verification of IMRT fields. Br J Radiol; 92:20190355 6. Carlson JNK et al. (2016). Phys Med Biol; 61:2514–2531 7. Babier A et al. (2021). Med Phys; 48(9):5549-5561 8. Court LE et al. (2023). J Vis Exp; (200) 9. Gooding MJ et al. (2024). Fully automated RT planning challenge. Radiother Oncol; 200:110513 Keywords: Human factors, automation, AI

1580

Digital Poster Medical Physics Education Course: AAPM/HUG/UAMP Initiative for a Resilient Ukraine

Serhii Brovchuk 1,2 , Ruslan Zelinskyi 3 , Victoria Ainsworth 4 , William Swanson 5 , Robert Krauss 6 , Kelly Kisling 7 , Thomas A Brown 8 , Sean Dresser 9 , Julie Ann Raffi 10 , Jatinder R. Palta 11 , Wilfred Ngwa 12 , Stephen Avery 13 , Peter Sandwall 14 , Shada Wadi-Ramahi 15 , Matthew Goss 16 , Nataliya Kovalchuk 17