ESTRO 2020 Abstract book

S159 ESTRO 2020

CT-images. Our model can be used for late cardiac toxicity studies to evaluate the relationship between cardiac substructure doses and late cardiac disease. PH-0287 Transfer learning and Deep Neural Network for lung and heart dose prediction in breast treatments J. Perez-Alija 1 , P. Gallego 1 , M. Lizondo 1 , J. Nuria 1 , A. Latorre-Musoll 1 , I. Valverde-Pascual 1 , M. Barceló-Pagès 1 , N. Garcia-Apellaniz 1 , P. Carrasco de Fez 1 , P. Delgado- Tapia 1 , P. Simon Garcia 1 , M. Adria Mora 1 , A. Ruiz Martinez 1 , M. Ribas 1 , E. Ambroa 2 1 Hospital de la Santa Creu i Sant Pau, Medical Physics, Barcelona, Spain ; 2 Consorci Sanitari de Terrassa, Medical Physics Unit- Radiation Oncology Department, Terrassa, Spain Purpose or Objective Generating a convolutional neural network (CNN) model to predict lung and heart dose-volume histograms (DVH) in breast cancer patients with lymph nodes treated with 3D- CRT would help in the technique decision process. Usually, the work done in dose prediction using CNNs does not consider the plan quality of the training data. To ensure this quality, we propose a method for outliers detection within the dataset that can be used as a DVH predictor. Material and Methods We selected 195 patients with left breast cancer treated with 3D-CRT. We included patients with axillary and supraclavicular lymph nodes but excluded those with an internal mammary nodal (IMN) chain. For the model creation, we trained the CNN renormalizing all plans to 2 Gy/fraction, to take into account different prescribed doses. For our CNN model, we implemented a transfer learning approach using a pre-trained VGG-16 and replacing its three last layers with a fully connected neural network. Input data was the planning CT contour information. Output was a 2D lung and heart DVH for every slice. All slices were subsequently added up to account for the final whole OAR DVH. For the outliers detection, we partitioned our set in training, validation, and test (176, 10, and 10 patients, respectively). First, we trained the CNN with early stopping. Second, we evaluated how good our model fitted the data in the test set and searched for the presence of any potential outlier using the sum of residuals method to measure the discrepancy between the predicted and the clinical approved DVH; we defined an outlier as any prediction having a sum of residuals greater than one standard deviation from the population mean value. Finally, we repeated this two-step process using different partitions, until all the patients contained in the first training set were once in the test set. At every iteration, we initialized all the CNN parameters to avoid information bleeding. Once we selected all potential outliers, one researcher (M.L.) proceeded to re-optimized all the plans. We recalculated the sum of residuals for them and elaborated a confusion matrix with the model results. Results Our CNN model detected a total of 23 out of 195 patients as having a suboptimal plan. After the reoptimization step, all patients but one were not considered as an outlier anymore. Our false-positive result was of a patient with an IMN chain. We consequently excluded this patient from our dataset since having an IMN was an exclusion criterion. Figure I shows the clinically approved, replanned, and predicted, with confidence intervals, lung and heart DVHs for three patients where the model was applied.

Conclusion We validated our CNN model as a reliable method to account for outliers within a dataset. We developed an accurate model for DVH prediction in breast cancer patients. This work will allow us to discriminate beforehand which patients will not fulfill dose constraints with 3DCRT and would benefit from other techniques. PH-0288 Independent external validation of a logistic regression NTCP model for grade 3 oral mucositis M. Sharabiani 1 , E. Clementel 1 , N. Andratschke 2 , C. Fortpied 1 , V. Grégoire 3 , J. Overgaard 4 , J. Willmann 1 , C. Hurkmans 5 1 European Organization for Research and Treatment of Cancer EORTC, Headquarters, Brussels, Belgium ; 2 University Hospital Zürich- University of Zurich, Department of Radiation Oncology, Zürich, Switzerland ; 3 Léon Bérard Cancer Center, Radiation Oncology Department, Lyon, France ; 4 Aarhus University Hospital, Department of Experimental Clinical Oncology, Aarhus, Denmark ; 5 Catharina Hospital, Department of Radiation Oncology, Eindhoven, The Netherlands Purpose or Objective A logistic regression NTCP model has been previously developed to extract predictive variables and corresponding regression coefficients for incidence of grade 3 oral mucositis 1 . This model, however, has not been externally validated. Regarding the significance of external validation of NTCP models, especially using independent, unseen datasets, our goal was to evaluate the performance of a logistic regression model using the EORTC HNCG-ROG 1219 DAHANCA trial as the validation cohort. Material and Methods The training cohort was composed of 253 patients who received radiation alone or chemoradiation and treated with SIB-IMRT technique for head and neck squamous cell carcinoma. Logistic regression with bootstrapping was performed to extract the model’s predictive factors. The final logistic regression model revealed that the incidence of grade 3 oral mucositis was only dependent on the mean