ESTRO 2025 - Abstract Book

S129

Invited Speaker

ESTRO 2025

Objective The aim of this lecture is to review the SFRT techniques currently applied in clinical practice and under development, review the current state of clinical SFRT application, and provide an overview of the technical aspects and clinical experience in the practical implementation of SFRT at our center.

Learning outcomes

Describe SFRT techniques

•

• Identify the different types of SFRT modalities • Analyze the current status of SFRT treatment planning in clinical applications • Illustrate our center’s experience in the practical implementation of SFRT, focusing on treatment planning, quality assurance and delivery process • Discuss challenges, limitations and future perspectives Conclusion By the end of this lecture, attendees will have an overview of SFRT techniques and a practical guide example for their clinical application.

4866

Speaker Abstracts AI in radiation oncology education Simon L Duke Clinical Oncology, Cambridge University Hospitals - NHS, Cambridge, United Kingdom. School of Clinical Medicine, University of Cambridge, Cambridge, United Kingdom

Abstract:

There has never been a more exciting time for digital education in medicine with the advent of large language models, increasing sophistication of virtual and augmented reality, and software that can break down geographic and economic barriers to learning. This session explores the transformative potential of artificial intelligence (AI) to enhance the learning experience for radiation oncology trainees and practicing physicians alike, moving beyond traditional didactic methods towards personalised, adaptive, and engaging educational paradigms. • Personalise learning pathways: AI algorithms could analyse a trainee's performance, identify knowledge gaps, and tailor learning materials accordingly. AI could incorporate complex and effective learning strategies such as elaboration and interactive case studies, maximising efficiency and knowledge retention. • Automate assessment and feedback: AI could automate the assessment of knowledge and some skills, such as clinical reasoning - providing rapid, objective and consistent feedback to trainees. • Create realistic simulations: AI could power realistic simulations of complex clinical scenarios and skills such as communication, decision making, and contouring. These simulations would allow trainees to practice these critical skills in a safe, controlled environment. Imagine a future where AI-powered platforms can:

This session will delve into these possibilities, showcasing practical examples of how AI is already being used in medical education and outlining a roadmap for its implementation in radiation oncology. We will also discuss ethical