Investigating conditional GAN performance with different generator architectures, an ensemble model, and different MR scanners for MR-sCT conversion
Investigating conditional GAN performance with different generator architectures, an ensemble model, and different MR scanners for MR-sCT conversion
复制标题
DOI：
10.1088/1361-6560/ab857b
复制
发表时间：
2020-05-21
影响因子：
3.5
通讯作者：
Kuess, Peter
中科院分区：
文献类型：
--
作者：
Fetty, Lukas;Loefstedf, Tommy;Kuess, Peter
磁共振（MR）到合成计算机断层扫描（sCT）转换的最新发展表明，治疗计划是可能的，而无需初始计划CT。最近使用条件生成对抗网络（cGAN）证明了有希望的转换结果。然而，性能通常仅在来自一个MR扫描仪的图像上进行测试，这忽略了神经网络找到一般高级抽象特征的潜力。在这项研究中，我们探讨了在单个场强扫描仪上训练的发生器模型对用更高场强采集的数据的可推广性。纳入了51例接受前列腺癌（40例）和宫颈癌（11例）治疗的患者的T2加权0.35T MRI和CT。其中25个用于训练四种不同的生成器（SE-ResNet，DenseNet，U-Net和Embedded Net）。此外，从四个网络输出创建了一个集成模型。在0.35T MR扫描仪上对16例患者进行了验证。此外，在Gold Atlas数据集上测试了训练模型，该数据集包含不同场强的T2加权MR扫描; 1.5T（7）和3 T（12），以及来自0.35T扫描仪的10名患者。使用临床VMAT计划对所有受试患者的sCT进行剂量学比较。对于相同的扫描仪（0.35 T），不同型号的结果在测试集上具有可比性，平均绝对误差（MAE）（35- 51 HU主体）仅存在微小差异。对于3个型号的3 T GE Signa和3 T GE Discovery图像（40- 62 HU MAE）的转换，获得了相似的结果。然而，在1.5T图像（48- 65 HU MAE）中观察到较大的差异。总体上最好的模型被认为是合奏模型。所有剂量差异均低于1%。这项研究表明，可以将在一台扫描仪的图像上训练的模型推广到其他扫描仪和不同的场强。最好的度量结果是通过所有网络的组合来实现的。
Recent developments in magnetic resonance (MR) to synthetic computed tomography (sCT) conversion have shown that treatment planning is possible without an initial planning CT. Promising conversion results have been demonstrated recently using conditional generative adversarial networks (cGANs). However, the performance is generally only tested on images from one MR scanner, which neglects the potential of neural networks to find general high-level abstract features. In this study, we explored the generalizability of the generator models, trained on a single field strength scanner, to data acquired with higher field strengths. T2-weighted 0.35T MRIs and CTs from 51 patients treated for prostate (40) and cervical cancer (11) were included. 25 of them were used to train four different generators (SE-ResNet, DenseNet, U-Net, and Embedded Net). Further, an ensemble model was created from the four network outputs. The models were validated on 16 patients from a 0.35T MR scanner. Further, the trained models were tested on the Gold Atlas dataset, containing T2-weighted MR scans of different field strengths; 1.5T(7) and 3T(12), and 10 patients from the 0.35T scanner. The sCTs were dosimetrically compared using clinical VMAT plans for all test patients. For the same scanner (0.35T), the results from the different models were comparable on the test set, with only minor differences in the mean absolute error (MAE) (35-51HU body). Similar results were obtained for conversions of 3T GE Signa and the 3T GE Discovery images (40-62HU MAE) for three of the models. However, larger differences were observed for the 1.5T images (48-65HU MAE). The overall best model was found to be the ensemble model. All dose differences were below 1%. This study shows that it is possible to generalize models trained on images of one scanner to other scanners and different field strengths. The best metric results were achieved by the combination of all networks.