ESTRO 2023 - Abstract Book

S52

Saturday 13 May

ESTRO 2023

Conclusion Combining 3D information of the dose distribution, CT and swallowing-related segmentations in a DL model showed an improved prediction of late dysphagia compared to conventional NTCP models based on discrete dose parameters. Currently these models are in the process of being externally validated to evaluate their generalizability. OC-0089 Radiomics models from chest CT scan to predict brain metastases in radically treated stage III NSCLC H. Zeng 1 , F. Tohidinezhad 2 , D. De Ruysscher 3 , J. Degens 4 , V. van Kampen-van den Boogaart 5 , C. Pitz 6 , L. Hendriks 7 , A. Traverso 3 1 GROW School for Oncology and Reproduction, Maastricht University Medical Centre+ , Department of Radiation Oncology (Maastro), Maastricht, The Netherlands; 2 GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Department of Radiation Oncology (Maastro), , Maastricht, The Netherlands; 3 GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Department of Radiation Oncology (Maastro), Maastricht, The Netherlands; 4 Zuyderland Medical Center, , Department of Respiratory Medicine, Heerlen, The Netherlands; 5 VieCuri Medical Centre, Department of Pulmonology Diseases, Venlo, The Netherlands; 6 Laurentius Hospital, Department of Pulmonary Diseases, Roermond, The Netherlands; 7 GROW - School for Oncology and Reproduction, Maastricht University Medical Center+, Department of Pulmonary Diseases, , Maastricht, The Netherlands Purpose or Objective To develop radiomics models for predicting brain metastases (BM) development in patients with stage III non-small cell lung cancer (NSCLC) using the planning contrast-enhanced chest CT for thoracic radiotherapy (TRT). Materials and Methods Patients with stage III NSCLC treated in Maastro between 2012-2021 were screened. Eligibility criteria: adequately staged with 18FDG-PET and brain imaging, treated with definitive chemoradiotherapy, no thoracic surgery before TRT. Exclusion criteria: other malignancy within 5 years; no available planning CT. The time to BM was calculated from pathological diagnosis to imaging confirmed BM or last follow-up if no event was observed. The regions of interest (ROIs) were the gross tumor volume (GTV), primary lung tumor (GTVp), and metastatic lymph nodes (GTVn). GTV was the sum of GTVp and GTVn. Radiomics features were respectively extracted for GTV, GTVp, and GTVn using Pyradiomics. Competing risk analysis was used to identify significant features for BM, in which death without BM was considered a competing event. Bootstrapping samples with 500 iterations was performed to train models. Spearman correlations were performed for features that were significant in univariate analysis. Significant correlated features were removed and the ones with the highest hazard ratio (HR) were included in the multivariate model. Area under the receiver operating characteristic curves (AUC-ROC) was performed to assess model predictive performance. Results In total, 296 out of 497 patients were eligible, 157 (53%) were male, 112 (37.8%) were squamous cell,160 (54.1%) were stage IIIA, and 73 (24.7%) received immunotherapy. The median age was 66y (IQR 60-72). Within a median follow up of 55.3