ESTRO 2023 - Abstract Book

S30

Saturday 13 May

ESTRO 2023

and test dataset. The goal of the current study was to test the generalizability of these models by exploring their performance in another external validation dataset. Materials and Methods As part of the HECKTOR 2022 challenge, we developed and trained a radiomics, a deep-learning (DL) and a hybrid model on the provided training dataset including 481 OPC patients from 7 centers and tested them on the independent dataset with 339 OPC patients from 3 centers. In total, 219 OPC patients that were treated in our institution were included for the current external validation. The primary tumor and pathologic lymph nodes (GTVp+n) were auto contoured and used as input for RFS prediction. The radiomics model variables were weight, HPV status, surface area and Run Length Non Uniformity of the GTVp+n on CT scan. The DL model input included weight, chemotherapy, gender, age, the PET scan and the GTVp+n contour. The hybrid model was the DL-model in combination with the risk output of the radiomics model. The c-index of each model was calculated in our external dataset. Kaplan Meier (KM) curves were made where patients were stratified into high and low risk groups by the median value of the predicted risk. The log-rank test was used to compare the two risk groups. Results The validation performance of the radiomics (c-index=0.67), DL (c-index=0.67) and hybrid model (c-index=0.68) in our external set was good and was comparable with the performances in the HECKTOR test set (Table 1). The KM-curves of the three models showed good and significant separation in the high and low RFS risk groups (Figure 1). The radiomics model with interpretable imaging biomarkers achieved the same performance as the DL-model. The hybrid model showed the best performance in the training and our external set, yet its generalizability may be lower as suggested by the lower performance in the HECKTOR test set. Table 1. C-indexes of the three models

Figure 1. Kaplan-Meier (KM) curves of the three models

Conclusion Radiomics, DL and hybrid models for RFS prediction all showed good performance when validated in our external OPC dataset. Since the radiomics model is the most interpretable, this may be the most promising tool for the prediction of RFS

and can contribute to a more individualized treatment. Poster Discussion: Palliative radiotherapy & SBRT

PD-0063 Final results of a randomized trial on accelerated radiotherapy in bone metastases (NCT03503682) A. Zamagni 1 , G. Siepe 2 , S. Bisello 1,2 , E. Scirocco 3,2 , F. Candoli 1,2 , F. Deodato 4,5 , G. Macchia 4 , F. Fiorica 6 , E. Farina 7 , S. Cilla 8 , I. Ammendolia 2 , L. Caravatta 9 , C. Malizia 10 , S. Cammelli 1,2 , F. Cellini 5,11 , A.G. Morganti 3,2 1 Department of Experimental Diagnostic and Specialty Medicine – DIMES, University of Bologna, Bologna, Italy; 2 Radiation Oncology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy; 3 Department of Experimental Diagnostic and Specialty Medicine – DIMES , University of Bologna, Bologna, Italy; 4 Radiation Oncology Unit, Gemelli Molise Hospital – Università Cattolica del Sacro Cuore, Campobasso, Italy; 5 Istituto di Radiologia, Università Cattolica del Sacro Cuore, Roma, Italy; 6 Department of Radiation Oncology and Nuclear Medicine, AULSS 9 Scaligera, Verona, Italy; 7 Department of Radiation Oncology, Sant'Anna University Hospital of Ferrara, Ferrara, Italy; 8 Medical Physics Unit, Gemelli Molise Hospital – Università Cattolica del Sacro Cuore, Campobasso, Italy; 9 Department of Radiation Oncology, SS. Annunziata Hospital, "G. D'Annunzio" University of Chieti, Chieti, Italy; 10 Nuclear Medicine, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy; 11 Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, 10. Fondazione Policlinico Universitario "A. Gemelli" Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Roma, Italy Purpose or Objective SHARON BONE is a phase III randomized controlled multicenter trial aiming to demonstrate non-inferior symptoms relief of hypofractionated accelerated palliative radiotherapy (RT; 20 Gy in 4 fractions twice a day) versus a standard RT regimen (30 Gy in 10 daily fractions), in painfully complicated bone metastases. Materials and Methods