ESTRO 2023 - Abstract Book

S1357

Digital Posters

ESTRO 2023

based delineations adhere better to the DBCG guidelines than the clinical ground truths.

Median scored patients showed minor disagreements in the cranio-caudal extension, varying 1-2 slices and an overall acceptable agreement in width, range of difference 0.64-1.35mm.

Conclusion We demonstrated the feasibility of developing a clinically relevant DL model for CTVn_IMN based on real world clinical delineations. The model exhibited minor deviations from clinical ground truth for most patients. In patients with major deviations, model predictions were closer to DBCG guidelines than ground truth. The largest differences were in the caudal extension, indicating that in a clinical setting, attention should be focused on this region. To further mitigate variations, a dataset created specifically for the purpose of training a DL model would be needed.

PO-1656 autoencoder-based quality assurance of deep learning segmentation of parotid glands in HNC patients

S.W. Zijlstra 1 , A. de Biase 2,3 , C. Brouwer 2 , S. Both 2 , J. Langendijk 2 , P. van Ooijen 2

1 University of Twente, Faculty of Science and Technology, Enschede, The Netherlands; 2 University Medical Centre Groningen (UMCG), Department of Radiotherapy, Groningen, The Netherlands; 3 University Medical Centre Groningen (UMCG), Data Science Centre in Health (DASH), Groningen, The Netherlands Purpose or Objective In radiotherapy, the pre-treatment planning of head and neck cancer (HNC) patients includes the segmentation of organs at risk (OARs) as observed on Computed Tomography (CT) images. In our clinical practice, Deep Learning Contours (DLCs)