ESTRO 2025 - Abstract Book

S67

Invited Speaker

ESTRO 2025

applications to address them effectively. One of the key issues is that AI is often developed to optimize individual steps in the workflow without questioning whether the overall process itself could be improved. A broader perspective may reveal opportunities for AI-driven workflow redesign, rather than incremental improvements to traditional methods and workflows. In addition, a comprehensive approach should also evaluate how AI integrates with other technological advancements in brachytherapy, ensuring that the combination of innovations leads to the most effective and efficient treatment strategies. Despite rapid advancements in AI for prostate brachytherapy, its clinical impact remains limited by a technology first rather than a needs-driven approach. By prioritizing the identification of critical areas for AI intervention and establishing clear criteria for its integration, we can move towards a more effective and clinically meaningful application of AI in prostate brachytherapy. This presentation will illustrate these challenges and opportunities through concrete clinical examples. References Barten, D.L.J., Pieters, B.R., Bouter, A., van der Meer, M.C., Maree, S.C., Hinnen, K.A., Westerveld, H., Bosman, P.A.N., Alderliesten, T., van Wieringen, N., & Bel, A. (2023). Towards artificial intelligence-based automated treatment planning in clinical practice: A prospective study of the first clinical experiences in high-dose-rate prostate brachytherapy. Brachytherapy, 22 (2), 279-289. Bélanger, C., Aubin, S., Beaulieu, L., & Poulin, E. (2022). Commissioning of GPU-based multi-criteria optimizer combined with plan navigation tools for high-dose-rate brachytherapy. Journal of Contemporary Brachytherapy, 14 (3), 181-188. https://doi.org/10.5114/jcb.2022.118995 Breedveld, S., Bennan, A.B.A., Aluwini, S., Schaart, D.R., Kolkman-Deurloo, I.K.K., & Heijmen, B.J.M. (2023). Fast automated multi-criteria planning for HDR brachytherapy explored for prostate cancer. Physics in Medicine & Biology, 68 (4), 045003. https://doi.org/10.1088/1361-6560/acb4f8 Chen, J., Qiu, R.L.J., Wang, T., Momin, S., & Yang, X. (2024). A review of artificial intelligence in brachytherapy. Journal of Radiation Oncology and Medical Physics, 51 (1), 45-63. Fionda, B., Placidi, E., de Ridder, M., De Spirito, M., Sala, E., & Tagliaferri, L. (2024). Artificial intelligence in interventional radiotherapy (brachytherapy): Enhancing patient-centered care and addressing patients’ needs. Clinical and Translational Radiation Oncology, 49 , 100865.

4752

Speaker Abstracts Dosimetry of brachytherapy boost: LDR versus HDR Frank-André Siebert UKSH, Campus Kiel, Clinic of Radiotherapy, Kiel, Germany

Abstract: Brachytherapy boost is a common and very successful technique for local prostate cancer in unfavourable and high risk stage. Dose escalation can be given either as low-dose rate (LDR) or high-dose rate (HDR) brachytherapy. The application of these two techniques is quite similar and usually performed using ultrasound-based with the patient in lithothomy position. In the GEC-ESTRO guidelines from 2022 [1] the methods are well described. Dose precription is standardized for LDR boost with 110 Gy using Pd-103 or I-125, but less standardized for the HDR boost in the past. However, in [1] a single dose with 15 Gy to the CTV is recommended for the boost. It can therefore be assumed that the dose will be standardised over the years. Using LDR permanent treatment the dose is shaped by the position of the sources (seeds) only. When using HDR also the dwell times of the sources can be varied and used to shape the dose. To obtain fast and user-independent treatment plans, inverse treatment planning can be used for both treatment methods. HDR treatment plans are more robust in terms of tissue composition. Due to the high energy, calcifications in the prostate are not as relevant with HDR brachytherapy as with LDR brachytherapy [2] where it can be up to 37% of D90 with 1 -5% calcifications in