ESTRO 2023 - Abstract Book

S81

Saturday 13 May

ESTRO 2023

For real-time iDL, the radiation oncologist only used one round of iDL. For this, he annotated 16, 10, and seven slices for the first round of iDL per patient, respectively. After the update, three, one, and two slices were manually annotated to achieve clinically acceptable segmentations. Conclusion We presented a slice-based iDL segmentation tool which needs only limited input from observers. During the iDL simulation, annotating three to five slices substantially improved the segmentation accuracy. In real-time iDL, our tool was able to provide a satisfactory result after two rounds of annotation. OC-0120 Validation of a deep-learning segmentation model for HNC patients in various treatment positions L. Chen 1,2,3,4 , P. Platzer 5 , C. Reschl 1 , M. Schafasand 1,6 , A. Nachankar 7,8 , C.L. Hajdusich 1 , P. Kuess 6 , M. Stock 1,9 , S. Habraken 2 , A. Carlino 1 1 MedAustron Ion Therapy Center, Department of Medical Physics, Wiener Neustadt, Austria; 2 Erasmus MC Cancer Institute, University Medical Center, Department of Radiotherapy, Rotterdam, The Netherlands; 3 Delft University of Technology, Faculty of Mechanical, Maritime and Materials Engineering, Delft, The Netherlands; 4 Leiden University Medical Center, Faculty of Medicine, Leiden, The Netherlands; 5 Fachhochschule Wiener Neustadt, Department of MedTech, Wiener Neustadt, Austria; 6 Medical University of Vienna, Department of Radiation Oncology, Vienna, Austria; 7 MedAustron Ion Therapy Center, Department of Medicine, Wiener Neustadt, Austria; 8 ACMIT Gmbh, Department of Medicine, Wiener Neustadt, Austria; 9 Karl Landsteiner University of Health Sciences, Department of Oncology, Krems an der Donau, Austria

Purpose or Objective