ESTRO 2022 - Abstract Book

S1440

Abstract book

ESTRO 2022

absolute error (MAE), root mean square error (RMSE), the coefficient of determination R 2 , and fitted line plots showing the relationship between the predicted and delivered positions. Results The MAE during validation for support vector, linear regression, random forest, XGBoost, and ANN were 0.210, 0.205, 0.188, 0.220, and 0.179 mm, respectively. The RMSE during validation for support vector, linear regression, random forest, XGBoost, and ANN were 0.122, 0.121, 0.285, 0.335, and 0.096 mm, respectively. The MAE and RMSE achieved by each model during testing are reported in the same order as the metrics reported for validation (support vector, linear regression, random forest, XGBoost, and ANN). The maximum MAE achieved during testing on leaves from Y1 bank were 0.335, 0.337, 0.300, 0.332, and 0.296 mm, and the RMSE were 0.474, 0.478, 0.452, 0.479, and 0.441 mm. The maximum MAE achieved during testing on leaves from Y2 bank were 0.518, 0.516, 0.532, 0542, and 0.508 mm, and the RMSE were 0.721, 0.726, 0.745, 0.667, and 0.709 mm. All models achieved a R 2 value of 0.999 on the training, validation, and testing datasets. Table 1 summarizes the results for the training, validation, and testing datasets. Fitted-line plots for each model showing the relationship between the predicted and delivered positions for one leaf is shown in Figure 1. The results show that the models’ performance on leaves from the Y2 bank were worse than their performance on leaves from the Y1 bank.

Conclusion Although the models show higher errors on leaves from the Y2 bank, the ANN still slightly outperformed the other models in predicting the leaf positions for VMAT plans. Including more data and with further model tuning, these errors can be reduced further, thus improving the model accuracy.

PO-1645 Treatment planning protocol in Single-Dose Radiation Therapy for prostate cancer

D. Panizza 1,2 , R. Lucchini 3,2 , V. Faccenda 1,4 , P. Caricato 1,4 , E. De Ponti 1,2 , S. Arcangeli 3,2

1 ASST Monza, Medical Physics Department, Monza, Italy; 2 University of Milan Bicocca, School of Medicine and Surgery, Milan, Italy; 3 ASST Monza, Radiation Oncology Department, Monza, Italy; 4 University of Milan, Department of Physics, Milan, Italy Purpose or Objective Great emphasis on rigorous planning and delivery techniques must be placed when using extreme hypofractionated regimens to fully exploit their potential benefits in optimizing the therapeutic ratio, thus yielding excellent clinical outcomes. The aim of this study was to report the clinical treatment planning implementation for organ-confined linac-based prostate Single-Dose Radiation Therapy (SDRT) using electromagnetic tracking for real-time intrafraction organ motion management (NCT04831983). Materials and Methods Since June 2021 five patients with localized unfavorable intermediate or selected high-risk prostate tumors were enrolled to receive an ultra-high SDRT of 24 Gy (BED 1.5 = 408 Gy). Patients were simulated with empty rectum and bladder filled by a Foley catheter. Fused CT and T2W 3D MRI image sets were used to delineate target and OARs. The PTV consisted of the CTV with a 2-mm isotropic margin. A high-dose avoidance zone (HDAZ) was created by a 3-mm expansion around the