ESTRO 2023 - Abstract Book

S1983

Digital Posters

ESTRO 2023

Forty-eight male albino Sprague-Dawley rats were divided into six groups. Irradiation (IR) group: total cranial IR with a single dose of 5 Gray (Gy) was administered to the rats. CAPE plus IR group: rats in this group received total cranial IR with a single dose of 5 Gy and intraperitoneal (IP) injection of CAPE (10 µmol kg-1day-1) 30 minutes before IR . Propolis plus IR group: rats received total cranial IR with a single dose of 5 Gy and propolis (80 mg kg-1day-1) via an orogastric tube one hour before IR. Control group of propolis: rats in this group received 1-ml of saline via an orogastric tube. Control group of CAPE: rats in this group received DMSO by IP injections equal to the volume of CAPE in the CAPE group. Sham group: rats in this group did not receive IR, propolis, or CAPE. Oxidative and antioxidant status parameters were examined in the kidney tissue of rats. Oxidative parameters; lipid hydroperoxide (LOOH) levels, total oxidant status (TOS), and oxidative stress index (OSI), and antioxidant parameters; total antioxidant status (TAS), total sulfhydryl (–SH) levels, paraoxonase, ceruloplasmin, and arylesterase activities were determined. ANOVA test was used to analyze the differences between groups in normally distributed variables. Kruskal Wallis H test was used for abnormal distributed data. Results Kidney TOS, OSI, and LOOH levels were found significantly higher in the IR group than all other groups (P <0.001). TAS and –SH levels in the IR group were significantly lower compared to propolis plus IR, CAPE plus IR, and sham group (P <0.001). Total –SH levels in the propolis plus IR group were found higher than CAPE plus IR group (P <0.001). Furthermore –SH levels were increased in CAPE plus IR group compared to the sham group (P <0.001). Statistically significant changes were not detected between groups in terms of paraoxonase, arylesterase, and ceruloplasmin activities. Conclusion Cranial ionizing radiation exposure leads formation of free radicals. These free radicals may be released to the systemic circulation and cause oxidative stress in kidneys. Propolis and CAPE may enhance antioxidant capacity and prevent kidney tissue from radiation-induced oxidative damage in rats. 1 Maastricht University Medical Centre+, Department of Radiation Oncology (Maastro), GROW School for Oncology, Maastricht, The Netherlands; 2 Chongqing University of Posts and Telecommunications, Key Laboratory of Data Engineering and Visual Computing, Chongqing, China; 3 Maastricht University Medical Centre+, Maastro, Maastricht, The Netherlands; 4 Maastricht University Medical Centre+, Department of Radiation Oncology (Maastro), Maastricht, The Netherlands Purpose or Objective Radiation pneumonitis (RP) is a common side effect of thoracic radiation treatment and relevant for patients’ quality of life receiving RT. Researchers are investigating DL methods for RP prediction in planning RT scans. However, the massive data requirements of deep learning have long been a limitation in the field, especially for RP prediction, where it is often difficult (and sometimes impossible) to obtain enough training data to build a robust RP detection algorithm. Until now, there is no study that can generate RP synthetic images to overcome the deficiencies of insufficient data and data imbalance. We proposed a mask self-attention mechanism-based GAN (shown in Figure 1) to generate RP CT images to overcome the above deficiencies. PO-2203 Generation of synthetic radiation pneumonitis images using deep learning Z. Wang 1 , J. Liu 2 , Y. Zhang 2 , Z. Zhang 3 , A. Dekker 4 , A. Traverso 4

Figure 1. The structure of proposed method. G and F are two generators that generate normal lungs and pneumonic lungs, respectively. Dx is the discriminator to distinguish whether the image is real. Materials and Methods CT images and dose files were obtained from 300 patients diagnosed with lung cancer who received radical radiotherapy at Tianjin cancer hospital between 2013 to 2019. Of these 62 were diagnosed with RP. Two experiments were used to prove the utility of our algorithm. For the first experiment, the model was trained by unpaired patients with and without RP. Then the heat map of the differences between the synthetic RP images and original