文献速递中枢神经肿瘤放疗放疗物理与技术

基于深度学习的脑部伪CT剂量学质量评估:MRI-only放疗计划关键参数影响

Dosimetry-Driven Quality Measure of Brain Pseudo Computed Tomography Generated From Deep Learning for MRI-Only Radiation Therapy Treatment Planning.
PubMed 文献 · Int J Radiat Oncol Biol Phys · 2020-05-14

采用平均绝对误差、gamma指数和剂量体积直方图评价,发现训练集超过200例时伪CT质量更优,T1与T1-Gd模型gamma指数最大差异仅0.07个百分点,不同预处理下剂量学质量保持等效。

要点

  • 训练集超过200例时生成的伪CT质量更高。
  • 仅用T1与仅用T1-Gd训练对性能无显著影响。
  • 白条纹预处理平均绝对误差78±22 HU,略优于其他方法。

核心结论

  • 使用超过200例训练数据可生成最佳伪CT,T1与T1-Gd训练性能无显著差异,不同预处理下剂量学质量等效且可用于临床。

研究设计与样本

  • 采用3D卷积神经网络将MRI映射为CT,评估训练集大小、MRI序列、4种标准化方法及偏场校正的影响。
  • 比较HighResNet与3D UNet两种网络架构对伪CT质量的影响。

主要发现

  • 使用全部可用病例训练时伪CT质量更高。
  • T1与T1-Gd模型的gamma指数均值最大差异为0.07个百分点。
  • 白条纹标准化的平均绝对误差为78±22 HU,略优于直方图、零均值/单位方差和无标准化(P < .0001)。
  • HighResNet和3D UNet的3%/3 mm gamma指数分别为99.83%±0.19%和99.74%±0.24%。

关键数值与推荐

  • 训练集超过200例样本时伪CT质量更优。
  • 白条纹标准化平均绝对误差78±22 HU(P < .0001 vs 其他方法)。
  • HighResNet 3%/3 mm gamma指数99.83%±0.19%,3D UNet为99.74%±0.24%。

临床怎么用

  • 建议训练集超过200例以保证伪CT质量。
  • T1或T1-Gd序列均可用于训练,性能无显著差异。
  • 不同预处理下剂量学质量等效,可根据流程选择标准化方法。

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

PURPOSE: This study aims to evaluate the impact of key parameters on the pseudo computed tomography (pCT) quality generated from magnetic resonance imaging (MRI) with a 3-dimensional (3D) convolutional neural network. METHODS AND MATERIALS: Four hundred two brain tumor cases were retrieved, yielding associations between 182 computed tomography (CT) and T1-weighted MRI (T1) scans, 180 CT and contrast-enhanced T1-weighted MRI (T1-Gd) scans, and 40 CT, T1, and T1-Gd scans. A 3D CNN was used to map T1 or T1-Gd onto CT scans and evaluate the importance of different components. First, the training set size's influence on testing set accuracy was assessed. Moreover, we evaluated the MRI sequence impact, using T1-only and T1-Gd-only cohorts. We then investigated 4 MRI standardization approaches (histogram-based, zero-mean/unit-variance, white stripe, and no standardization) based on training, validation, and testing cohorts composed of 242, 81, and 79 patients cases, respectively, as well as a bias field correction influence. Finally, 2 networks, namely HighResNet and 3D UNet, were compared to evaluate the architecture's impact on the pCT quality. The mean absolute error, gamma indices, and dose-volume histograms were used as evaluation metrics. RESULTS: Generating models using all the available cases for training led to higher pCT quality. The T1 and T1-Gd models had a maximum difference in gamma index means of 0.07 percentage point. The mean absolute error obtained with white stripe was 78 ± 22 Hounsfield units, which slightly outperformed histogram-based, zero-mean/unit-variance, and no standardization (P < .0001). Regarding the network architectures, 3%/3 mm gamma indices of 99.83% ± 0.19% and 99.74% ± 0.24% were obtained for HighResNet and 3D UNet, respectively. CONCLUSIONS: Our best pCTs were generated using more than 200 samples in the training data set. Training with T1 only and T1-Gd only did not significantly affect performance. Regardless of the preprocessing applied, the dosimetry quality remained equivalent and relevant for potential use in clinical practice.

来源:Int J Radiat Oncol Biol Phys,查看原文。版权归原作者所有。

引用

  1. Alvarez Andres E, Fidon L, Vakalopoulou M, et al. Dosimetry-Driven Quality Measure of Brain Pseudo Computed Tomography Generated From Deep Learning for MRI-Only Radiation Therapy Treatment Planning. Int J Radiat Oncol Biol Phys. 2020. PMID: 32417412. doi:10.1016/j.ijrobp.2020.05.006

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。