ESTRO 2024 - Abstract Book

S4472

Physics - Machine learning models and clinical applications

ESTRO 2024

Conclusion:

NTCP model performance improvement is possible with deep learning NTCP modelling to predict taste loss at 6 months. With further optimization and the addition of attention maps, appreciation of this new 3D modelling approach can help better model and understand the very complex toxicity of radiation-induced taste loss in HNC patients.

Keywords: NTCP model, deep learning, Taste loss

1381

Digital Poster

Deep learning-based dose prediction for INTRABEAM

Mojahed Abushawish 1,2 , Arthur V Galapon 1,3 , Joaquín L Herraiz 1,4 , José M Udías 1,4 , Paula Ibáñez 1,4

1 University Complutense of Madrid, Nuclear Physics Group & IPARCOS, Madrid, Spain. 2 CNRS, Délégation Rhône Auvergne, Lyon, France. 3 University Medical Center Groningen, Department of Radiation Oncology, Groningen, Netherlands. 4 Clinical hospital San Carlos, Health research institute, Madrid, Spain