文献速递头颈部肿瘤放疗放疗物理与技术

基于生成对抗网络由MR生成合成CT用于鼻咽癌放疗计划

Magnetic resonance-based synthetic computed tomography images generated using generative adversarial networks for nasopharyngeal carcinoma radiotherapy treatment planning.
PubMed 文献 · Radiother Oncol · 2020-07-03

本研究从173例鼻咽癌患者的MR与CT图像中随机选取28例作为独立测试集,其余用于构建cGAN和cycleGAN两种生成对抗网络以合成CT(SCT)。cGAN由形变配准的MR-CT图像对训练,cycleGAN由未配准图像训练。结果显示两种方法均可快速生成准确SCT,cGAN在HU误差和剂量学精度上更优。

要点

  • cGAN和cycleGAN均可由MR快速生成鼻咽癌IMRT计划用SCT图像。
  • cGAN体部平均绝对HU误差69.67±9.27 HU,优于cycleGAN的100.62±7.39 HU。
  • cGAN的2%/2-mm γ通过率98.68±0.94%,ROI内绝对剂量偏差0.49±0.24%。

核心结论

  • cGAN与cycleGAN均可快速由MR生成准确的SCT体积图像,对鼻咽癌IMRT计划具有高剂量学精度。
  • 若有高质量MR-CT图像对,cGAN是更优选择。

研究设计与样本

  • 回顾性研究,纳入173例鼻咽癌患者的常规T1加权MR和CT图像。
  • 随机选取28例作为独立测试集,其余图像用于构建cGAN和cycleGAN。
  • cGAN生成器为U-net,使用形变配准的MR-CT图像对训练;cycleGAN生成器为残差U-net,使用未配准的MR和CT图像训练。

主要发现

  • cGAN和cycleGAN体部平均绝对HU误差分别为69.67±9.27 HU和100.62±7.39 HU。
  • cGAN和cycleGAN的2%/2-mm γ通过率分别为(98.68±0.94)%和(98.52±1.13)%。
  • cGAN和cycleGAN在感兴趣区内的绝对剂量偏差分别为(0.49±0.24)%和(0.62±0.36)%。

关键数值与推荐

  • HU误差评估采用体部平均绝对误差,cGAN为69.67±9.27 HU,cycleGAN为100.62±7.39 HU。
  • 剂量学评估采用2%/2-mm γ通过率和ROI内绝对剂量偏差,cGAN分别为(98.68±0.94)%和(0.49±0.24)%,cycleGAN分别为(98.52±1.13)%和(0.62±0.36)%。

临床怎么用

  • 在具备高质量配准MR-CT图像对时,可优先考虑cGAN生成SCT用于鼻咽癌IMRT计划。
  • 无配准图像对时,cycleGAN也可作为备选,但其HU精度和剂量学精度略低于cGAN。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND AND PURPOSE: To investigate the feasibility of synthesizing computed tomography (CT) images from magnetic resonance (MR) images using generative adversarial networks (GANs) for nasopharyngeal carcinoma (NPC) intensity-modulated radiotherapy (IMRT) planning. MATERIALS AND METHODS: Conventional T1-weighted MR images and CT images were acquired from 173 NPC patients. The MR and CT images of 28 patients were randomly chosen as the independent tested set. The remaining images were used to build a conditional GAN (cGAN) and a cycle-consistency GAN (cycleGAN). A U-net was used as the generator in cGAN, whereas a residual-Unet was used as the generator in cycleGAN. The cGAN was trained using the deformable registered MR-CT image pairs, whereas the cycleGAN was trained using the unregistered MR and CT images. The generated synthetic CT (SCT) images from cGAN and cycleGAN were compared with the true CT images with respect to their Hounsfield Unit (HU) discrepancy and dosimetric accuracy for NPC IMRT plans. RESULTS: The mean absolute errors within the body were 69.67 ± 9.27 HU and 100.62 ± 7.39 HU for the cGAN and cycleGAN, respectively. The 2%/2-mm γ passing rates were (98.68 ± 0.94)% and (98.52 ± 1.13)% for the cGAN and cycleGAN, respectively. Meanwhile, the absolute dose discrepancies within the regions of interest were (0.49 ± 0.24)% and (0.62 ± 0.36)%, respectively. CONCLUSION: Both cGAN and cycleGAN could swiftly generate accurate SCT volume images from MR images, with high dosimetric accuracy for NPC IMRT planning. cGAN was preferable if high-quality MR-CT image pairs were available.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. Peng Y, Chen S, Qin A, et al. Magnetic resonance-based synthetic computed tomography images generated using generative adversarial networks for nasopharyngeal carcinoma radiotherapy treatment planning. Radiother Oncol. 2020. PMID: 32622781. doi:10.1016/j.radonc.2020.06.049

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。