ESTRO 2025 - Abstract Book

S19

Invited Speaker

ESTRO 2025

radiotherapy (WPRT). The study identified two key texture features—Run Entropy (RE-GLRLM) and Small Area Emphasis (SAE-GLSZM)—significantly correlated with patient outcomes. The model demonstrated strong predictive performance (AUC: 0.76 training, 0.71 testing), offering a practical, non-invasive tool for routine prognosis in high risk prostate cancer patients. These projects highlight the unique contributions of radiation therapists in radiomics research. By leveraging our access to planning CT images and our deep understanding of treatment regimes, radiation therapists can extract meaningful insights from imaging data and integrate them with clinical knowledge to develop robust predictive models. Our familiarity with treatment planning, dose delivery, and patient outcomes positions us as ideal stake holders in this research area, enabling us to bridge the gap between technical data analysis and clinical application. Building on these pilot projects, I lead a newly funded study: "Personalized Prediction of Acute Genitourinary Toxicities of Prostate Stereotactic Body Radiotherapy: A Combined Retrospective-Prospective Study." This project, in collaboration with five hospitals in Hong Kong, aims to develop a personalized prediction model for acute genitourinary (GU) toxicities in prostate cancer patients undergoing stereotactic body radiotherapy (SBRT). By addressing the multifactorial nature of GU toxicity, this research seeks to improve patient care through tailored treatment planning, dose optimization, and targeted interventions for high-risk patients. Finally, I will issue a call to action, inviting radiation therapists to join this research initiative. Participants can contribute their expertise in various ways, such as sharing clinical insights to guide the development of clinically relevant radiomics models, assisting with technical tasks like imaging data analysis and feature extraction using tools like PyRadiomics, and contributing to the collection and curation of high-quality imaging and clinical datasets. Multicenter collaboration is also encouraged to expand the scope of research and essentially to enhance the generalizability of findings. Most importantly, joining this initiative allows radiation therapists to play a pivotal role in improving patient care. By contributing to the development of radiomics models, radiation therapists can help personalize treatment strategies, predict toxicities, and optimize outcomes for cancer patients. This is an opportunity to make a tangible difference in patients' lives while advancing the radiation therapy profession. Together, we can harness the power of radiomics to make a lasting impact on patient care. Join me in this exciting journey to shape the future of radiation therapy research and ensure that radiation therapists remain at the forefront of innovation in cancer treatment!

4677

Speaker Abstracts Maximise radiation therapy simulations Yolanda Surjan, Leah Cramp, Debra Lee, Laura Feighan Global Centre for Research and Training in Radiation Oncology, The University of Newcastle, Newcastle, Australia

Abstract:

Simulation in Radiation Therapy Simulation-based learning has the potential to become the foundation in the education of radiation therapy students, offering a controlled, risk-free environment to develop essential skills before applying them in clinical settings. This approach provides numerous advantages, making it an invaluable tool in training future health professionals. Some of these advantages and benefits include: Enhanced Clinical Skills in a Risk-Free Environment In radiation therapy, precision and accuracy are paramount. Simulation-based learning allows students to practice and refine their techniques without the pressure of real-world consequences. By using advanced simulation tools, learners can perform complex procedures, such as treatment planning and delivery, in a controlled setting. This helps build confidence and competence before transitioning to actual patient care.