ESTRO 2022 - Abstract Book

S690

Abstract book

ESTRO 2022

Results

Applying the trained revGAN to the three planes of a single patient ( Fig1 ) required about 10s. A mean absolute error of 71±14HU (mean±std) was obtained in the body contours intersection between CT and sCT (Tab1). A dose difference of 0.8±1.0% was obtained on the D>90% of the prescribed dose, with a mean γ -2%,2mm pass rate of 97.8±1.0% ( Tab1 ).

Conclusion Accurate MR-based dose calculation from MR-based sCT is feasible for lung cancer patients, enabling MRI-only radiotherapy in an anatomical area affected by respiratory motion. This study motivates the development of MR-only RT for lung advocating for a clinical study on a larger cohort.

OC-0773 CBCT-to-CT synthesis using weakly-paired cycle-consistent generative adversarial networks

A. Szmul 1 , S. Taylor 1 , P. Lim 2 , J. Cantwell 2 , D. D’Souza 2 , S. Moinuddin 2 , M. Gaze 2 , J. Gains 2 , C. Veiga 1

1 University College London, Department of Medical Physics and Biomedical Engineering, London, United Kingdom; 2 University College London Hospitals NHS Foundation Trust, Radiotherapy Department, London, United Kingdom

Purpose or Objective Cycle-consistent generative adversarial

networks method for CBCT-to-CT synthesis for RT treatment verification and adaptation. However, current approaches cannot guarantee sufficient structural consistency between source and synthetic images. We propose a novel framework for CBCT-to-CT synthesis in abdominal paediatric patients, a rare and diverse population where collecting large and representative datasets for data- driven approaches is challenging. Materials and Methods A total of 50 CT and 183 CBCT scans from 50 patients aged 2 to 22 treated for malignancies in the thoracic-abdominal- pelvic region were used in this study. The data were randomly split as 40/10 patients for training and evaluation, respectively (40/10CTs, 152/31CBCTs). (cycleGANs) are a popular