ESTRO 2025 - Abstract Book

S3389

Physics - Machine learning models and clinical applications

ESTRO 2025

Conclusion: Meaningful uncertainty estimates in dose modelling are achievable with the three methods presented. MVE methods stood out for comparable performance and efficient implementation. Further investigation is needed for interpretability and examination on larger test datasets with out-of-domain situations.

Keywords: uncertainty estimation, dose calculation

References: [1] Tompson, Jonathan, et al. "Efficient object localization using convolutional networks." Proceedings of the IEEE conference on computer vision and pattern recognition . 2015. [2] Nix, David A., and Andreas S. Weigend. "Estimating the mean and variance of the target probability distribution." Proceedings of 1994 ieee international conference on neural networks (ICNN'94) . Vol. 1. IEEE, 1994.

1949

Digital Poster Complexity-based unsupervised machine learning for patient-specific VMAT quality assurance. Savino Cilla 1 , Carmela Romano 1 , Pietro Viola 1 , Maurizio Craus 1 , Gabriella Macchia 2 , Francesco Deodato 2 , Alessio G Morganti 3 1 Medical Physics Unit, Responsible Research Hospital, Campobasso, Italy. 2 Radiation Oncology Unit, Responsible Research Hospital, Campobasso, Italy. 3 9Department of Experimental, Diagnostic and Specialty Medicine - DIMES, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy Purpose/Objective: Patient-specific quality assurance (PSQA) is essential to guarantee the requested accuracy and safety of high precision radiotherapy treatments. The primary aim of this research was to investigate the potential of different unsupervised ML methods to unravel hidden patterns and groupings in PSQA data based on a clustering analysis of plan complexity.

Material/Methods: A total of 1329 pretreatment verification plans from 660 consecutive patients with different tumour sites treated