ESTRO 2025 - Abstract Book

S4360

RTT - Treatment planning, OAR and target definitions

ESTRO 2025

The main limitation of this study was the small sample of patients from just a single institution, which will not allow generalizing the results to the entire population. In any case, it is a starting point to have an acceptable PGI prediction considering the TV. Aspects such as coverage, prescription curve, and PCI performance must be maintained so that it is possible to predict according to this model. Conclusion: According to the data from this study, there appears to be a correlation in the value of the PGI with TV. An increase in the PGI value seems to be found for lesions with smaller volumes, steadying at values lower than 3 for larger volumes. A larger sample will be needed to confirm the results of this study. References: 1. Peña-Pino I, Chen CC. Stereotactic Radiosurgery as Treatment for Brain Metastases: An Update. Asian Journal of Neurosurgery. 2023 Jun 16;18(2):246. 2. Paddick I. A simple scoring ratio to index the conformity of radiosurgical treatment plans. 2000 Dec; 3. Paddick I, Lippitz B. A simple dose gradient measurement tool to complement the conformity index. J Neurosurg. 2006 Dec;105 Suppl:194–201. 4. Reynolds TA, Jensen AR, Bellairs EE, Ozer M. Dose Gradient Index for Stereotactic Radiosurgery/Radiation Therapy. Int J Radiat Oncol Biol Phys. 2020 Mar 1;106(3):604–11. Keywords: Gradient-Index, Target-Volume, Radiosurgery

2511

Digital Poster Evaluation of SAM and SAM2 from clinical perspective for organ delineation Borbála Deák-Karancsi, Zsófia Karancsi, Ádám Kékesi, Eszter Katalin Kiss, Luqman Muhammad Hakim, Krisztián Koós, László Ruskó HC STO-Artificial Intelligence & Machine Learning, GE Healthcare Magyarország Kft., Budapest, Hungary Purpose/Objective: The Segment Anything Model (SAM) serves as a versatile framework for interactive segmentation, particularly in medical imaging applications. Though this study primarily focuses on MR T2-weighted images, SAM can also be