ESTRO 2022 - Abstract Book

S135

Abstract book

ESTRO 2022

Results For single group input (Table 1 M1-M3), models based solely on clinical factors resulted in the highest ROC-AUC for predicting DFS and OS. For LRC prediction, however, models trained on textural features achieved the highest ROC-AUC scores. Concatenated models (Table 1 M4-M7) trained on multiple inputs performed similarly to those trained on single input, suggesting that there was no added gain by including more than one input. The highest performance was obtained using an ensemble of models (Table 1 M8-M12). The ensemble M11 of the single- input model M1 trained on clinical factors only and the multiple-input model M6 trained on radiomics features gave the highest ROC-AUC scores for all endpoints.

Conclusion Textural features extracted from PET/CT images were the best predictors of LRC, while clinical factors were more important for predicting DFS and OS. An ensemble of models trained on clinical factors and radiomics features separately can achieve overall good DFS, LRC and OS predictions.

PD-0160 Osteoradionecrosis of the mandible in head and neck cancer patients: dose-volume correlations

C. Muñoz-Montplet 1 , J. Marruecos 2 , I. Oliveras 3 , M. Foix 4 , D. Jurado-Bruggeman 1

1 Institut Català d'Oncologia, Medical Physics and Radiation Protection, Girona, Spain; 2 Institut Català d'Oncologia, Radiation Oncology, Girona, Spain; 3 Institut Català d'Oncologia, Radiation Oncology , Girona, Spain; 4 University of Barcelona, Physics Faculty, Barcelona, Spain

Purpose or Objective