ESTRO 2023 - Abstract Book

S132

Saturday 13 May

ESTRO 2023

Conclusion We set up a pipeline of pre-processing shared between different ML models and applied to a large cohort of patients to predict Acute Toxicity. As shown, no model performed the best for all metrics: more deep ML models have better performances, also if LR is not too different. For all of them we may quantify and see feature importance. This study is supported by ERAPERMED-2020-110-JTC. PD-0171 Survival prognostication in esophageal cancer using deep learning based segmentation features L. Volmer 1 , V. Prudente 2,1 , Z. Zhang 3 , A. Dekker 1,3 , M. Berbee 1 , L. Wee 1,4 1 Radiation Oncology (MAASTRO), Maastricht University Medical Centre, Maastricht, The Netherlands; 2 Maastricht University, CARIM School for Cardiovascular Diseases, Maastricht, The Netherlands; 3 Maastricht University, GROW School of Oncology, Maastricht, The Netherlands; 4 Maastricht University, GROW School of Oncology , Maastricht, The Netherlands Purpose or Objective Esophageal cancer (EC) has a poor prognosis (estimated 1-year overall survival of approximately 50%). Individualized treatment selection is complicated by multiple treatment options and a lack of reliable prognostic models . Radiomics is a promising opportunity for analysis, but requires a delineation of the Gross Tumour Volume (GTV) by a physician. This study examines (a) the accuracy of automated segmentation of the GTV on planning CT series using deep learning and (b) whether deep radiomics features within a segmentation network might have prognostic potential for overall survival (OS). Materials and Methods Clinical features and planning CTs were extracted for 406 subjects single Dutch institution treated by either definitive (DCRT) or neoadjuvant (NACRT) chemoradiotherapy for locally advanced EC. These were randomly split into training (n=325) and validation (n=81). An independent test set comprised of 52 subjects previously treated in a clinical trial (CROSS ). Each GTV was defined by a qualified radiotherapy oncologist and taken “as-treated” from the RT plan. A squeeze and excitation segmentation network was trained to automatically segment GTV using an Adam optimizer and a compound (Focal and Dice) loss function. Deep features were extracted from intermediate convolutional layers using global average pooling, and used as predictors in a deep learning time-to-event network for OS. The Dice similarity coefficient (DSC) was used to quantify geometric segmentation agreement, and Harrell’s concordance index (HCI) was used to evaluate discriminative performance. Confidence intervals were estimated via bootstrap resampling. Results In the test set, the mean DSC was 0.72 (range 0.26-0.86). The HCI for OS at 2 years were: 0.65 (95% confidence interval 0.64-0.65), 0.66 (0.66-0.67) and 0.68 (0.68-0.69), for deep features only, clinical features only (age, sex, tumour location, treatment intent, T-stage, N-stage and tumour volume) and a combination of (clinical + deep) features, respectively. Conclusion Deep learning automatic segmentation was able to make a reasonable estimate of the GTV on hitherto unseen planning CT series. The deep features from segmentation taken to a deep learning survival model appear to contain prognostic information regarding OS. The combination of clinical and deep features leads to a small increase in discriminative performance. PD-0172 NTCP model prediction considering RBE variability in proton therapy of primary brain tumors F. Hennings 1,2 , M. Palkowitsch 3,2 , J. Eulitz 3 , A. Seidlitz 3,4,5,7 , E.G. Troost 6,2,7,4,5 , M. Krause 3,2,7,4,5 , J. Bensberg 8 , C. Hahn 6,7,8 , F. Heinzelmann 9,10,11 , C. Bäumer 9,10,11 , A. Lühr 8 , B. Timmermann 9,10,11 , S. Löck 3,7,4,5 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, Institute of Radiooncology – OncoRay, Dresden, Germany; 3 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; 4 German Cancer Consortium (DKTK), partner site

Made with FlippingBook flipbook maker