Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy
Deep learning-based synthetic CT generation for paediatric brain MR-only photon and proton radiotherapy
复制标题
DOI：
10.1016/j.radonc.2020.09.029
复制
发表时间：
2020-12-01
影响因子：
5.7
通讯作者：
Philippens, Marielle E. P.
中科院分区：
文献类型：
--
作者：
Maspero, Matteo;Bentvelzen, Laura G.;Philippens, Marielle E. P.
背景和目的：为了实现精确的基于磁共振成像（MRI）的剂量计算，需要生成合成计算机断层摄影（sCT）图像。我们的目的是评估的可行性，从MRI获得的成像协议的异构集为儿科患者受脑tumors.Materials和方法：60例接受脑放射治疗的儿科患者的剂量计算。MR成像方案因患者而异，并且在训练/验证/测试集中保持数据异质性。训练三个2D条件生成对抗网络（cGAN），以从T1加权MRI生成sCT，考虑三个正交平面及其组合（多平面sCT）。对于每例患者，计算三个视图的中位数和标准差（sigma），分别获得组合sCT和不确定性图的代理。sCT进行了评估，对规划CT的图像相似性和准确性的光子和质子剂量calculations.Results：平均绝对误差为61 +/- 14 HU（平均值+/- 1西格玛），在CT和sCT之间的身体轮廓的交叉点。组合的多平面sCT的性能优于任何单一平面的sCT。不确定性图强调多平面sCT在身体轮廓和气腔方面不同。在D >处方剂量的90%和平均γ时，获得了-0.1 +/- 0.3%和0.1 +/- 0.4%的剂量差异（2%; 2 mm）光子和质子计划的通过率分别为99.5 +/- 0.8%和99.2 +/- 1.1%。使用三个正交平面的组合进行sCT生成的精确的基于MR的剂量计算对于儿科脑癌患者是可行的，即使在异构数据集上进行训练时也是如此。(C)2020作者（S）由爱思唯尔公司出版
Background and Purpose: To enable accurate magnetic resonance imaging (MRI)-based dose calculations, synthetic computed tomography (sCT) images need to be generated. We aim at assessing the feasibility of dose calculations from MRI acquired with a heterogeneous set of imaging protocol for paediatric patients affected by brain tumours.Materials and methods: Sixty paediatric patients undergoing brain radiotherapy were included. MR imaging protocols varied among patients, and data heterogeneity was maintained in train/validation/test sets. Three 2D conditional generative adversarial networks (cGANs) were trained to generate sCT from T1-weighted MRI, considering the three orthogonal planes and its combination (multi-plane sCT). For each patient, median and standard deviation (sigma) of the three views were calculated, obtaining a combined sCT and a proxy for uncertainty map, respectively. The sCTs were evaluated against the planning CT in terms of image similarity and accuracy for photon and proton dose calculations.Results: A mean absolute error of 61 +/- 14 HU (mean +/- 1 sigma) was obtained in the intersection of the body contours between CT and sCT. The combined multi-plane sCTs performed better than sCTs from any single plane. Uncertainty maps highlighted that multi-plane sCTs differed at the body contours and air cavities. A dose difference of -0.1 +/- 0.3% and 0.1 +/- 0.4% was obtained on the D > 90% of the prescribed dose and mean gamma(2%; 2 mm) pass-rate of 99.5 +/- 0.8% and 99.2 +/- 1.1% for photon and proton planning, respectively.Conclusion: Accurate MR-based dose calculation using a combination of three orthogonal planes for sCT generation is feasible for paediatric brain cancer patients, even when training on a heterogeneous dataset. (C) 2020 The Author(s). Published by Elsevier B.V.