ESTRO 2023 - Abstract Book

S251

Saturday 13 May

ESTRO 2023

Conclusion As hypothed, the PTV volume was decreasing, while the high dose region in relation to the actual PTV is stable for the IMRT-MR-Linac plan and fluctuating with the VMAT-CBCT plans. Although the high dose volume was high, the coverage of the VMAT plans was reduced to 85.3%. In the salivary glands, this resulted in a reduction of the volume receiving more than 95% prescribed dose of 3%, while the mean dose was similar. PD-0316 Deep learning tumor segmentation for target delineation in glioblastoma using multi-parametric MRI M. Hannisdal 1 , D. Goplen 2 , S. Alam 3 , J. Haasz 4 , L. Oltedal 5 , M.A. Rahman 6 , C.B. Rygh 5 , S.A. Lie 7 , A. Lundervold 3 , M. Chekenya 6 1 Haukeland University Hospital, Dept of Oncology and Medical Physics, Bergen, Norway; 2 Haukeland University Hospital, Dept of Oncology, Bergen, Norway; 3 Mohn Medical Imaging and Visualization Centre, Radiology, Bergen, Norway; 4 Haukland University Hospital, Radiology, Bergen, Norway; 5 Haukeland University Hospital, Radiology, Bergen, Norway; 6 University of Bergen, Biomedicine, Bergen, Norway; 7 University of Bergen, Clinical Odontology, Bergen, Norway Purpose or Objective High precision tumor delineation is a prerequisite for optimal RT treatment planning that enables precise organ-at-risk sparing and reduction of adverse effects. However, manual tumor delineation remains laborious and challenging due to radiological complexity. The objective of this study was to investigate the feasibility of the HD-GLIO tool, an ensemble of pre-trained deep learning models based on the nnUNet algorithm, for glioblastoma tumor segmentation. Materials and Methods In a collection of 29 multi-parametric standard MRI examinations from 13 glioblastoma patients, we compared the predicted contrast-enhanced (CE) and non-enhancing (NE) output volumes from HD-GLIO segmentation and the corresponding manual delineations obtained by two independent expert operators (Figure 1). The output of HD-GLIO was compared by Dice Similarity Coefficient and Hausdorff 95% (HD95) to: (i) the manual delineations of each observer separately, emphasizing differences across disciplines, (ii) the fused label, being the union and joint contribution from two disciplines to the manual delineations, and (iii) the aforementioned labels with added isotropic dilations, representing margins clinically used in RT. We also assessed the volume consistency between measures by inter item intraclass correlation coefficient (ICC).