Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy
Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy
复制标题
使用生成对抗网络进行基于多序列 MR 图像的合成 CT 生成，仅用于头颈 MRI 放射治疗
DOI：
10.1002/mp.14075
复制
发表时间：
2020-02-26
期刊：
影响因子：
3.8
通讯作者：
Song, Ting
中科院分区：
文献类型：
--
作者：
Qi, Mengke;Li, Yongbao;Song, Ting
目的本研究旨在探讨不同磁共振（MR）序列对复杂头颈部区域基于深度学习的合成计算机断层扫描（sCT）生成准确性的影响。方法收集45例鼻咽癌患者的4个MR图像序列（T1、T2、T1C和T1DixonC-water）。使用不同序列（单通道）和不同组合（多通道）作为输入来训练七个条件生成对抗网络（cGAN）模型。为了进一步验证cGAN的性能，我们还使用了U-net网络作为比较。对实际 CT 和不同模型生成的 sCT 之间的平均绝对误差、结构相似性指数、峰值信噪比、骰子相似系数和剂量分布进行了评估。结果结果表明，以多通道（即 T1 + T2 + T1C + T1DixonC-water）作为输入来预测 sCT 的 cGAN 模型比任何单一 MR 序列模型具有更高的准确性。 T1 加权 MR 模型比 T2、T1C 和 T1DixonC-water 模型取得了更好的结果。 cGAN 和 U-net 之间的比较表明，cGAN 预测的 sCT 保留了额外的图像细节，模糊程度更小，并且与实际 CT 更相似。 结论 以多个 MR 序列作为模型输入的条件生成对抗网络显示出最佳精度。 T1加权MR图像提供了足够的图像信息，适合采集序列或采集时间有限的临床场景中的sCT预测。
Purpose The purpose of this study is to investigate the effect of different magnetic resonance (MR) sequences on the accuracy of deep learning-based synthetic computed tomography (sCT) generation in the complex head and neck region.Methods Four sequences of MR images (T1, T2, T1C, and T1DixonC-water) were collected from 45 patients with nasopharyngeal carcinoma. Seven conditional generative adversarial network (cGAN) models were trained with different sequences (single channel) and different combinations (multi-channel) as inputs. To further verify the cGAN performance, we also used a U-net network as a comparison. Mean absolute error, structural similarity index, peak signal-to-noise ratio, dice similarity coefficient, and dose distribution were evaluated between the actual CTs and sCTs generated from different models.Results The results show that the cGAN model with multi-channel (i.e., T1 + T2 + T1C + T1DixonC-water) as input to predict sCT achieves higher accuracy than any single MR sequence model. The T1-weighted MR model achieves better results than T2, T1C, and T1DixonC-water models. The comparison between cGAN and U-net shows that the sCTs predicted by cGAN retains additional image details are less blurred and more similar to the actual CT.Conclusions Conditional generative adversarial network with multiple MR sequences as model input shows the best accuracy. The T1-weighted MR images provide sufficient image information and are suitable for sCT prediction in clinical scenarios with limited acquisition sequences or limited acquisition time.