ESTRO 2023 - Abstract Book

S352

Sunday 14 May 2023

ESTRO 2023

Co-registration between 3D radiology and 2D histology is a challenging problem, especially for H&N for which the larynx on WSI is often halved. We solve it through an automatic deep learning framework, which is by construction also able of generating synthetic images from one modality to the other one. It paves the way for a better understanding of the tissue microenvironment by overlaying histology-based features on the radiological acquisition, while the reconstruction task enables the generation of noninvasive virtual biopsy. Such tools should yield more precise and personalized RT treatment.

Proffered Papers: Toxicity modelling

OC-0449 Deep learning based NTCP-modelling using 3D-information for predicting late xerostomia H. Chu 1 , S.P. de Vette 1 , H. Neh 1 , N.M. Sijtsema 1 , R.J. Steenbakkers 1 , C.D. Fuller 2 , J.A. Langendijk 1 , P.M. van Ooijen 1 , L.V. van Dijk 1 1 University Medical Center Groningen, Radiotherapy, Groningen, The Netherlands; 2 MD Anderson Cancer Center, Radiation Oncology, Houston, USA Purpose or Objective Normal tissue complication probability (NTCP) models aim to predict radiation-induced toxicities. Conventional NTCP- models are typically logistic regression models that are based on discrete input variables. For xerostomia, a common radiation-induced toxicity for head and neck cancer (HNC) patients, current NTCP prediction is based on mean dose to salivary glands and baseline complaints. These features contain limited spatial information and thus may lack information required for more accurate xerostomia predictions. Deep learning (DL) models have the potential to improve the prediction of xerostomia as they utilize full 3-dimensional (3D) dose distributions and image information, rather than using 1D dose representations. The aim of this study was to develop a DL-based NTCP-model to predict xerostomia 12 months after HNC radiotherapy and to compare the prediction performance to a conventional NTCP-model. Materials and Methods In total, 898 HNC patients were included that were treated with radiotherapy between 2007 and 2021. The cohort was split in a training (70%), internal validation (15%) and independent test (15%) set. The endpoint was patient-rated moderate-to- severe xerostomia after 12 month of radiotherapy (EORTC QLQ-H&N35). The 3D dose distributions, CT scans, organs-at-risk (OARs) contours and baseline xerostomia score were DL input (Figure 1). The following architectures were considered and optimized individually (i.e., hyperparameter tuning): 1) EfficientNet-v2; 2) residual neural network (ResNet), and: 3) deep convolutional neural network (DCNN). Model performance was evaluated with area under the curve (AUC) criteria in the validation and test cohort. DL model performance was compared to that of the recently published xerostomia NTCP model by Van den Bosch et al. (2019), which includes the mean dose to salivary glands and baseline xerostomia score. Finally, attention maps were created to visualize regions of the input image where the DL model focused on when making predictions.