ESTRO 2024 - Abstract Book

S4500

Physics - Machine learning models and clinical applications

ESTRO 2024

Figure 1. Example of clinical and predicted dose-volume histograms for each of the four different cases. Examples are median patients when the sum of relative OAR and PTV mean dose errors are considered. ln = regional lymph nodes, PTV = planning target volume with a 5mm marginal from the skin of the patient.

Conclusion:

We developed a deep learning-based dose prediction model for breast and regional lymph node irradiation using a modified U-net architecture. The model showed high accuracy and robustness in predicting the dose distribution for different cases. The deep learning-based framework has the potential to facilitate and enhance radiotherapy planning for breast cancer patients.