返回Google圖書搜尋

System Radiobiology Modelling of Radiation Induced Lung Disease

出版	McGill University Libraries, 2016
URL	http://books.google.com.hk/books?id=hU4WnQAACAAJ&hl=&source=gbs_api

註釋"Radiation induced lung disease (RILD) is a side effect of radiotherapy for treating thoracic cancers, limiting radiation dose to tumours and in turn the chance of treatment success. A current scheme for predicting and managing RILD risk is based on a population-based normal tissue complication probability (NTCP) model assuming the same response to given radiation dose in lung. However, recent research suggests that dose response can be modified by biological and clinical factors pertinent to pathogenesis of RILD. In this work, we explore systems radiobiology approaches to model RILD as a result of interactions between these factors. Clinical, dosimetric, and biological data on lung cancer patients were analyzed to identify markers associated with high RILD risk. Then, we applied machine learning methods to combine such markers into models that calculate patient-specific RILD risk. We investigated two RILD endpoints: radiation fibrosis (RF) and radiation pneumonitis (RP). RF is formation of scar tissues in lung and can be quantitatively measured from computed tomography (CT) images. We extended a classical NTCP model to explicitly model time-dependent dose response of RF risk. Our modelling results have shown significant change in dose-RF correlation after 3 months post-treatment as well as higher RF risk when tumour was in lower lung. We extended the dose modelling to intra-treatment CT images. However, we did not find association between early CT changes and biological states or clinical outcomes. Subsequent investigations on radiation pneumonitis (RP) also suggest that dose response is modified by factors not related to lung dose distribution, such as dose to heart or production of proteins that are responsible for inflammatory reactions. We built an ensemble of Bayesian Networks (BN) to represent inter-relationships between such variables. The BN was trained by fusing the observed data with prior knowledge on causal relations. In order to account for a fractionation effect on RILD, we modelled the conventional (2 Gy per fraction) and stereotactic body radiotherapy groups separately. Utility of the BN ensemble models for both groups was demonstrated in two ways: 1) robust prediction that can handle uncertainties in data, and 2) hypothesis-generating potential of the network topology that were derived from data. In conclusion, we created mathematical models for both early and late RILD that could be used for patient-specific RILD risk adaptive planning. We propose that clinical and biological risk factors should be considered in addition to dosimetry information. Finally, we advocate a use of Bayesian network as a systems radiobiology approach to combine these factors."--