ESTRO 2024 - Abstract Book

S3562

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

ESTRO 2024

Figure 1. Comparison between clinical and predicted dose: axial slice visualization (top) and dose volume histogram (bottom).

Conclusion:

The proposed CNN model trained to predict RT doses was successfully tested for treatments of prostate cancers. The DVHs obtained on the predicted doses were on par with the clinical ones. These results can further be used as input of a knowledge transfer system such as dose mimicking or DVH constraints extraction.

Keywords: Radiotherapy planning, Dose Prediction

1401

Proffered Paper

End-to-end automatic treatment planning for prostate radiotherapy

Rémi Vauclin 1 , Baris Ungun 1 , Edouard Delasalles 1 , Elie Mengin 1 , Norbert Bus 1 , Madalina-Liana Costea 2 , Gorkem Gungor 3 , Frederic Gassa 4 , Vincent Gregoire 4 , Pauline Maury 5,6 , Charlotte Robert 5,6 , Pascal Fenoglietto 7 , Nikos Paragios 8 1 TheraPanacea, Physcis, Paris, France. 2 TheraPanacea, Clinical Affairs, Paris, France. 3 Acibadem MAA University School of Medicine, Department of Radiation Oncology, Istanbul, Turkey. 4 Centre Léon Berard, Department of