Technical Note: U-net-generated synthetic CT images for magnetic resonance imaging-only prostate intensity-modulated radiation therapy treatment planning
Technical Note: U-net-generated synthetic CT images for magnetic resonance imaging-only prostate intensity-modulated radiation therapy treatment planning
复制标题
DOI：
10.1002/mp.13247
复制
发表时间：
2018-12-01
期刊：
影响因子：
3.8
通讯作者：
Yan, Di
中科院分区：
文献类型：
--
作者：
Chen, Shupeng;Qin, An;Yan, Di
目的 临床实施纯磁共振成像 (MRI) 放射治疗需要一种获取合成 CT 图像 (S-CT) 以进行剂量计算的方法。本研究调查了构建基于 MRI 的 S-CT 生成的深度卷积神经网络的可行性，并评估了前列腺 IMRT 计划的剂量测定准确性。方法 从 51 名前列腺癌患者中每人获取配对 CT 和 T2 加权 MR 图像。随机选择 15 对作为测试集，其余 36 对作为训练集。通过应用人工变形和馈送到包含 23 个卷积层和 2529 万个可训练参数的二维 U 网来增强训练对象。 U-net 表示一个非线性函数，输入 MR 切片并输出相应的 S-CT 切片。使用真实CT和S-CT图像之间的Hounsfield单位(HU)的平均绝对误差(MAE)来评估HU估计精度。使用真实的 CT 图像应用向 PTV 规定剂量 79.2 Gy 的 IMRT 计划。然后用 S-CT 图像替换真实 CT 图像，并根据同一计划重新计算剂量矩阵，并使用伽马指数分析和绝对点剂量差异与从真实 CT 获得的剂量矩阵进行比较。结果 使用 GP100-GPU 在 58.67 小时内从头开始训练 U-net。生成新的 S-CT 体积图像的计算时间为 3.84-7.65 s。在体内，MAE 的（平均值 +/- SD）为 (29.96 +/- 4.87) HU。 1%/1mm和2%/2mm伽玛合格率分别超过98.03%和99.36%。相对于处方，DVH 参数差异小于 0.87%，PTV 内最大点剂量差异小于 1.01%。结论 U-net 可以在几秒钟内从传统 MR 图像生成 S-CT 图像，并且前列腺 IMRT 计划的剂量测量精度较高。
Purpose Clinical implementation of magnetic resonance imaging (MRI)-only radiotherapy requires a method to derive synthetic CT image (S-CT) for dose calculation. This study investigated the feasibility of building a deep convolutional neural network for MRI-based S-CT generation and evaluated the dosimetric accuracy on prostate IMRT planning. Methods A paired CT and T2-weighted MR images were acquired from each of 51 prostate cancer patients. Fifteen pairs were randomly chosen as tested set and the remaining 36 pairs as training set. The training subjects were augmented by applying artificial deformations and feed to a two-dimensional U-net which contains 23 convolutional layers and 25.29 million trainable parameters. The U-net represents a nonlinear function with input an MR slice and output the corresponding S-CT slice. The mean absolute error (MAE) of Hounsfield unit (HU) between the true CT and S-CT images was used to evaluate the HU estimation accuracy. IMRT plans with dose 79.2 Gy prescribed to the PTV were applied using the true CT images. The true CT images then were replaced by the S-CT images and the dose matrices were recalculated on the same plan and compared to the one obtained from the true CT using gamma index analysis and absolute point dose discrepancy. Results The U-net was trained from scratch in 58.67 h using a GP100-GPU. The computation time for generating a new S-CT volume image was 3.84-7.65 s. Within body, the (mean +/- SD) of MAE was (29.96 +/- 4.87) HU. The 1%/1 mm and 2%/2 mm gamma pass rates were over 98.03% and 99.36% respectively. The DVH parameters discrepancy was less than 0.87% and the maximum point dose discrepancy within PTV was less than 1.01% respect to the prescription. Conclusion The U-net can generate S-CT images from conventional MR image within seconds with high dosimetric accuracy for prostate IMRT plan.