ESTRO 2025 - Abstract Book

S2926

Physics - Dose prediction, optimisation and applications of photon and electron planning

ESTRO 2025

RP, Figure 1 shows the generated plan alternatives. Figure 2 contrasts one of the risk-guided plans with a comparable risk-agnostic plan for a gain in the RP risk of 2.8% at the cost of minor spinal cord deterioration. Overall, we demonstrated that our method generates plans that improve patient-specific risk at acceptable cost to other objectives.

Fig. 1

Fig. 2

Conclusion: The inclusion of personalized risk models in multi-criteria plan generation can reduce the risk of radiation-induced cardiovascular disease and radiation pneumonitis.

Keywords: multi-criteria optimization, personalization

References: Bokrantz, R., & Forsgren, A. 2013. "An algorithm for approximating convex Pareto surfaces based on dual techniques." INFORMS Journal on Computing. Craft et al. 2012. "Improved planning time and plan quality through multicriteria optimization for intensity modulated radiotherapy." International Journal of Radiation Oncology* Biology* Physics. Isaksson et al. 2020. "Machine learning-based models for prediction of toxicity outcomes in radiotherapy." Frontiers in oncology. Maragno et al. 2024. "Embedding machine learning based toxicity models within radiotherapy treatment plan optimization." Physics in Medicine & Biology.