ESTRO 38 Abstract book

S254 ESTRO 38

planning CT for dosimetry analysis. The recurrences were defined as in-field, marginal or out-of-field, according to dose-volume histogram (DVH) of the recurrence volume. To explore the predictive power of radiomics for NPCs with in-field recurrences (NPC-IFR), 16 NPCs with non- progression disease (NPC-NPD) were used for comparison. For these NPC-IFRs and NPC-NPDs, 1117 radiomic features were quantified from the tumor region using pre- treatment spectral attenuated inversion-recovery T2- weighted (SPAIR T2W) magnetic resonance imaging (MRI). Intraclass correlation coefficients (ICC) and Pearson correlation coefficient (PCC) was calculated to identify influential feature subset. Kruskal-Wallis test and receiver operating characteristic (ROC) analysis were employed to assess the capability of each feature on NPC-IFR prediction. Principal component analysis (PCA) was performed for feature reduction. Artificial neural network (ANN), k-nearest neighbor (KNN) and support vector machine (SVM) models were trained and validated by using stratified 10-fold cross validation.

Conclusion In-field and high-dose region relapse were the main recurrence patterns which may be due to the radioresistance. After integration in the clinical workflow, radiomic analysis can be served as imaging biomarkers to facilitate early salvage for NPC patients who are at risk of in-field recurrence. OC-0496 Deep-learning based estimation of loco- regional control for patients with locally advanced HNSCC S. Starke 1,2,3 , S. Leger 1,3,4 , A. Zwanenburg 1,3,4 , K. Pilz 1,3,4,5 , F. Lohaus 1,3,4,5 , A. Linge 1,3,4,5 , K. Zöphel 6,7 , J. Kotzerke 6,7 , A. Schreiber 8 , I. Tinhofer 9,10 , V. Budach 9,10 , M. Stuschke 11,12 , P. Balermpas 13,14 , C. Rödel 13,14 , U. Ganswindt 15,16,17 , C. Belka 15,16,17 , S. Pigorsch 15,18 , S.E. Combs 15,18,19 , D. Mönnich 20,21 , D. Zips 20,21 , M. Krause 1,3,4,5,22 , M. Baumann 1,3,4,5,22,23 , C. Richter 1,3,5,22 , E.G.C. Troost 1,3,4,5,22 , S. Löck 1,3,5 1 OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden- Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany ; 2 Helmholtz-Zentrum Dresden - Rossendorf, Department of Information Services and Computing, Dresden, Germany; 3 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site, Dresden, Germany; 4 National Center for Tumor Diseases NCT, Partner Site Dresden: German Cancer Research Center DKFZ Heidelberg- Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden and Helmholtz Association / Helmholtz-Zentrum Dre; 5 Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden, Department of Radiotherapy and Radiation Oncology, Dresden, Germany; 6 Faculty of Medicine and University Hospital Carl Gustav Carus- Technische Universität Dresden, Department of Nuclear Medicine, Dresden, Germany; 7 Helmholtz-Zentrum Dresden - Rossendorf, PET Center- Institute of Radiopharmaceutical Cancer Research, Dresden, Germany; 8 Hospital Dresden-Friedrichstadt, Department of Radiotherapy, Dresden, Germany ; 9 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site, Berlin, Germany; 10 Charité University Hospital, Department of Radiooncology and Radiotherapy, Berlin, Germany; 11 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site, Essen, Germany ; 12 Medical Faculty- University of Duisburg- Essen, Department of Radiotherapy, Essen, Germany; 13 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site, Frankfurt, Germany; 14 Goethe-University Frankfurt, Department of Radiotherapy and Oncology, Frankfurt, Germany ; 15 German Cancer Research Center DKFZ, Heidelberg and German Cancer Consortium DKTK partner site, Munich, Germany ; 16 Helmholtz Zentrum München, Clinical Cooperation Group- Personalized Radiotherapy

Results The median follow up was 26 (range 3-65) months. 13/26 (50%) occurred in the primary tumor, 8/26 (31%) occurred in regional lymph nodes, and 5/26 (19%) patients developed a primary and regional failure. Dosimetric and target volume analysis of the recurrence indicated that there were 24 in-field, and 1 marginal as well as 1 out-of- field recurrence. Among the HNCs with recurrence, 20 NPCs developed in-field failure (NPC-IFR). With pre- therapeutic SPAIR T2W MRI images available, 11 NPC-IFRs (11 of 20 NPC-IFRs who had available pre-therapeutic MRI) and 16 NPC-NPDs were subsequently employed for radiomic analysis. Results showed that NPC-IFRs versus NPC-NPDs could be differentiated by 8 features (AUCs: 0.727-0.835). The classification models showed potential in prediction of NPC-IFR with higher accuracies (ANN: 0.812, KNN: 0.775, SVM: 0.732).