Zeitschrift fur Medizinische Physik ( IF 2 ) Pub Date : 2023-08-01 , DOI: 10.1016/j.zemedi.2023.07.001 Attila Simkó 1 , Mikael Bylund 1 , Gustav Jönsson 1 , Tommy Löfstedt 2 , Anders Garpebring 1 , Tufve Nyholm 1 , Joakim Jonsson 1
The use of synthetic CT (sCT) in the radiotherapy workflow would reduce costs and scan time while removing the uncertainties around working with both MR and CT modalities. The performance of deep learning (DL) solutions for sCT generation is steadily increasing, however most proposed methods were trained and validated on private datasets of a single contrast from a single scanner. Such solutions might not perform equally well on other datasets, limiting their general usability and therefore value. Additionally, functional evaluations of sCTs such as dosimetric comparisons with CT-based dose calculations better show the impact of the methods, but the evaluations are more labor intensive than pixel-wise metrics.
To improve the generalization of an sCT model, we propose to incorporate a pre-trained DL model to pre-process the input MR images by generating artificial proton density, and maps (i.e. contrast-independent quantitative maps), which are then used for sCT generation. Using a dataset of only MR images, the robustness towards input MR contrasts of this approach is compared to a model that was trained using the MR images directly. We evaluate the generated sCTs using pixel-wise metrics and calculating mean radiological depths, as an approximation of the mean delivered dose.
On images acquired with the same settings as the training dataset, there was no significant difference between the performance of the models. However, when evaluated on images, and a wide range of other contrasts and scanners from both public and private datasets, our approach outperforms the baseline model.
Using a dataset of MR images, our proposed model implements synthetic quantitative maps to generate sCT images, improving the generalization towards other contrasts. Our code and trained models are publicly available.
中文翻译:
迈向与 MR 对比无关的合成 CT 生成
在放射治疗工作流程中使用合成 CT (sCT) 将降低成本和扫描时间,同时消除使用 MR 和 CT 模式的不确定性。用于 sCT 生成的深度学习 (DL) 解决方案的性能正在稳步提高,但大多数提出的方法都是在来自单个扫描仪的单个对比的私有数据集上进行训练和验证的。此类解决方案在其他数据集上可能表现不佳,从而限制了它们的一般可用性和价值。此外,sCT 的功能评估(例如与基于 CT 的剂量计算的剂量测定比较)可以更好地显示这些方法的影响,但评估比逐像素指标更加耗费人力。
为了提高 sCT 模型的泛化能力,我们建议结合预训练的 DL 模型,通过生成人工质子密度来预处理输入 MR 图像,和图(即与对比度无关的定量图),然后用于 sCT 生成。仅使用数据集MR 图像,该方法对输入 MR 对比度的鲁棒性与直接使用 MR 图像训练的模型进行了比较。我们使用像素级指标评估生成的 sCT,并计算平均放射深度,作为平均输送剂量的近似值。
在使用与训练数据集相同的设置获取的图像,模型的性能没有显着差异。然而,当评估图像以及来自公共和私人数据集的各种其他对比和扫描仪,我们的方法优于基线模型。
使用数据集MR 图像,我们提出的模型实现了合成定量图来生成 sCT 图像,提高了对其他对比的泛化能力。我们的代码和经过训练的模型是公开的。