Correlation between radiation-induced lung injury and 3D dose distribution(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2021年第6期
- Page:
- 692-698
- Research Field:
- 医学影像物理
- Publishing date:
Info
- Title:
- Correlation between radiation-induced lung injury and 3D dose distribution
- Author(s):
- FAN Xiaohong1; DONG Ke2; YANG Yin1; ZHANG Jianping1
- 1. School of Mathematics and Computational Science, Xiangtan University, Xiangtan 411105, China 2. Department of Radiotherapy, Xiangtan Central Hospital, Xiangtan 411101, China
- Keywords:
- Keywords: lung cancer dose distribution radiomics feature selection radiation-induced lung injury
- PACS:
- R318；R818.8
- DOI:
- DOI:10.3969/j.issn.1005-202X.2021.06.007
- Abstract:
- Abstract: Objective To analyze the correlation between radiation-induced lung injury and dose distribution in lung cancer patients by radiomics, and to determine the features related to CT image changes. Methods A total of 18 lung cancer patients who were followed-up after radiotherapy were enrolled in the study. The dose distribution of diagnostic CT was obtained from the deformation of planned CT dose distribution using the registration deformation field between planned CT and diagnostic CT. The ipsilateral and contralateral lungs and segmented lung parenchyma for each dose rang were considered as the regions of interest, and the radiomics features were extracted. The feature changes between before and after treatment were compared at different dose ranges and time, and the features with distinct differences were screened out. Results According to the dose-response curves of screening, 28 features at the 2nd week after radiotherapy which were significantly different from those at the 4th, 6th and 10th week after radiotherapy were selected, while the overall differences between the 4th week of radiotherapy and the 6th, 10th weeks after radiotherapy were relatively small. According to the dose-response curves of lung injury, 27 features which had stronger dose responses in the low dose area (0-20 Gy) or the high dose area (45-65 Gy) were selected, and the feature changes were larger with the longer time after radiotherapy. For the ipsilateral and contralateral lungs, 15 features which were obviously stratified were screened out. Conclusion By analyzing the features changes of lung cancer patients before and after radiotherapy, the significant correlation between radiation lung injury and three-dimensional dose distribution is confirmed. Monitoring the dynamic changes of these features has potential advantages in assessing the pattern of radioactive lung injury over time.
Last Update: 2021-06-29