ESTRO 2024 - Abstract Book

S4449

Physics - Machine learning models and clinical applications

ESTRO 2024

[1] Diamant A, Chatterjee A, Faria S, Naqa I El, Bahig H, Filion E, et al. Can dose outside the PTV influence the risk of distant metastases in stage I lung cancer patients treated with stereotactic body radiotherapy (SBRT)? Radiotherapy and Oncology 2018;128:513–9. https://doi.org/10.1016/j.radonc.2018.05.012. [2] Diamant A, Heng VJ, Chatterjee A, Faria S, Bahig H, Filion E, et al. Comparing local control and distant metastasis in NSCLC patients between CyberKnife and conventional SBRT. Radiotherapy and Oncology 2020;144:201–8. https://doi.org/10.1016/j.radonc.2020.01.017. [3] Hughes RT, Steber CR, Jacobson TJ, Farris MK. Impact of dose to lung outside the planning target volume on distant metastasis or progression after SBRT for early-stage non-small cell lung cancer. Radiotherapy and Oncology 2021;159:28–32. https://doi.org/10.1016/j.radonc.2021.03.004. [4] Lalonde R, Abdelhakiem M, Keller A, Huq MS. Dosimetric parameters related to occurrence of distant metastases and regional nodal relapse after SBRT for early-stage non-small cell lung cancer. Radiotherapy and Oncology 2022;169:90–5. https://doi.org/10.1016/j.radonc.2022.02.019.

932

Digital Poster

Forecasting model for qualitative prediction of the results of patient-specific quality assurance.

Tomasz Piotrowski 1,2,3 , Adam Ryczkowski 3,1 , Petros Kalendralis 4 , Barbara Bajon 3 , Marta Kruszyna-Mochalska 1,3 , Agata Jodda 3 1 Poznań University of Medical Sciences, Electroradiology, Poznań, Poland. 2 Adam Mickiewicz University, Biomedical Physics, Poznań, Poland. 3 Greater Poland Cancer Centre, Medical Physics, Poznań, Poland. 4 Maastricht University Medical Centre, Radiation Oncology, Maastricht, Netherlands

Purpose/Objective:

Analysis of the interrelations between planning and complexity metrics and gamma passing rates (GPR) results obtained from routinely realised volumetric modulated arc therapy (VMAT) treatments and building and examining the forecasting models for qualitative prediction of GPRs results.

Material/Methods:

802 treatment arcs from 379 VMAT treatment plans prepared for cancers localised in the head and neck, thorax, abdomen, and pelvic regions were analysed. The plans were verified by portal dosimetry and analysed twice using gamma analysis methods with 3%|2mm and 2%|2mm acceptance criteria. The tolerance limit of GPR was 95%. Three qualitative descriptors (QD) were established for GPR examination: red - the arcs for which the results of both analyses failed; green - the arcs for which the results of both analyses passed; and yellow - the rest of the arcs.