ESTRO 2022 - Abstract Book

S1410

Abstract book

ESTRO 2022

Conclusion Overall, LoCM can be used as a surrogate for TCM based Mid-V determination, if: • The autodelineation is qualitative and consistent over the phases •

Clinical evaluation is done on all phases, in three directions and on a movie loop • Considering that in case the tumour shows small movement (attached to the chestwall, vertebra or mediastinum) the LoCM might be less representative • When oscillatory motion is observed between LoCM and TCM, the tumour should be manually segmented

PO-1621 An efficient training approach for brain paediatrics synthetic CT generation for protontherapy

F. de Kermenguy 1 , E. Alvarez Andres 1 , L. De Marzi 2 , L. Fidon 3 , A. Carré 1 , S. Bolle 4 , N. Paragios 3 , E. Deutsch 1 , S. Ammari 4 , C. Robert 1 1 Gustave Roussy, UMR 1030 Radiothérapie Moléculaire et Innovation Thérapeutique, Villejuif, France; 2 Institut Curie, Proton Therapy Centre, Orsay, France; 3 TheraPanacea, Research department, Paris, France; 4 Gustave Roussy, Department of radiotherapy, Villejuif, France Purpose or Objective The increasing use of MRI in radiotherapy workflow has led to the development of "MRI-only" treatment planning methods, especially based on synthetic CT generation (sCT). Deep learning algorithms are the most attractive methods today for generating sCTs. However, the use of these algorithms requires a large amount of data, which can be critical in the case of paediatric patients, where cohorts are often small even when gathered from several centres and imagers. Thus, this study aims to compare four training methods based on a 3D HighResNet deep neural network architecture to generate sCTs for paediatric patients with brain tumours treated with protontherapy. The impact of using a learning strategy based on scans converted to relative stopping power (RSP) to avoid imager dependency while increasing cohort size was also studied. Materials and Methods A cohort of 394 adult patients including CT/MRI brain pairs (199 T1, 195 T1Gd) and a cohort of 198 paediatric patients including CT/MRI brain pairs (64 T1, 134 T1Gd) were used to train, validate and test a 3D HighResNet neural network. Pre- processing was applied to the images (N4 bias field correction, CT to MRI rigid registration, Z-score normalisation, intensity- clip, volume resampling). Except for method (1_HU), scan Hounsfield Units (HU) from 3 different devices set at 2 different high voltages (120 kVp and 135 kVp) were converted to RSP using stoechiometric calibration curves. Four methods of training and validation of the network were then compared: (1) paediatric-only (1_RSP and 1_HU), (2) adult-only, (3) mixed adult and paediatric, and (4) transfer learning with pre-training on adult patients before optimizing weights on the paediatric