文献速递肿瘤 PET/CT

基于深度学习的仅发射数据衰减校正方法在正电子发射断层成像中的比较

Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2021-12-09

本研究比较了两种仅利用发射PET数据和卷积神经网络(CNN)校正湮灭光子衰减的方法:μ-CNNNAC(从非衰减校正PET图像生成μ图)与μ-CNNMLAA(用CNN改进最大似然活动与衰减估计重建生成的μ图),并探讨两者结合(μ-CNNMLAA+NAC)及μ-CNNNAC用于提供MLAA所需散射分布的可行性。使用18F-FDG(n=100)或68Ga-DOTATOC(n=50)PET/CT图像训练和测试神经网络。结果显示μ-CNNNAC散射估计误差仅2.5%,但骨结构精度较低且肺μ值高估;μ-CNNMLAA及μ-CNNMLAA+NAC的活动图像优于μ-CNNNAC,但结合提升不显著。结论认为μ-CNNNAC用于散射估计可行,但μ-CNNMLAA优于μ-CNNNAC。

要点

  • μ-CNNNAC的衰减校正因子误差超过7%,但散射估计误差仅2.5%,提示其用于散射估计有效。
  • μ-CNNNAC提供的μ图中骨结构精度较低,肺μ值被高估;μ-CNNMLAA+NAC恢复精细骨结构效果最佳。
  • μ-CNNMLAA和μ-CNNMLAA+NAC的活动图像与λ-CT的相似性优于μ-CNNNAC,但两者结合提升不显著。

核心结论

  • 使用μ-CNNNAC进行散射估计以解决MLAA重建中的鸡生蛋难题是可行的,但μ-CNNMLAA优于μ-CNNNAC。

研究设计与样本

  • 研究使用18F-FDG(n=100)或68Ga-DOTATOC(n=50)PET/CT扫描的图像数据进行神经网络训练和测试。
  • 比较了仅用发射PET数据和CNN的两种衰减校正方法:μ-CNNNAC和μ-CNNMLAA,并研究了两者结合(μ-CNNMLAA+NAC)的性能提升及μ-CNNNAC提供MLAA所需散射分布的适用性。

主要发现

  • 使用μ-CT和μ-CNNNAC估计的衰减校正因子误差超过7%,但散射估计误差仅2.5%。
  • μ-CNNNAC提供的μ图中骨结构精度较低,肺μ值被高估;应用CNNMLAA+NAC恢复精细骨结构效果最佳。
  • 肺癌病灶百分比误差:λ-CNNNAC = 5.45% ± 7.88%,λ-CNNMLAA = 1.21% ± 5.74%,λ-CNNMLAA+NAC = 1.91% ± 4.78%。
  • 骨癌病灶百分比误差:λ-CNNNAC = 1.37% ± 5.16%,λ-CNNMLAA = 0.23% ± 3.81%,λ-CNNMLAA+NAC = 0.05% ± 3.49%。
  • 使用μ-CNNMLAA和μ-CNNMLAA+NAC衰减校正的活动图像(λ)在与λ-CT的相似性方面优于使用μ-CNNNAC校正的图像,但结合CNNNAC和CNNMLAA方法对相似性的提升不显著。

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 compare two approaches using only emission PET data and a convolution neural network (CNN) to correct the attenuation (μ) of the annihilation photons in PET. METHODS: One of the approaches uses a CNN to generate μ-maps from the non-attenuation-corrected (NAC) PET images (μ-CNNNAC). In the other method, CNN is used to improve the accuracy of μ-maps generated using maximum likelihood estimation of activity and attenuation (MLAA) reconstruction (μ-CNNMLAA). We investigated the improvement in the CNN performance by combining the two methods (μ-CNNMLAA+NAC) and the suitability of μ-CNNNAC for providing the scatter distribution required for MLAA reconstruction. Image data from 18F-FDG (n = 100) or 68 Ga-DOTATOC (n = 50) PET/CT scans were used for neural network training and testing. RESULTS: The error of the attenuation correction factors estimated using μ-CT and μ-CNNNAC was over 7%, but that of scatter estimates was only 2.5%, indicating the validity of the scatter estimation from μ-CNNNAC. However, CNNNAC provided less accurate bone structures in the μ-maps, while the best results in recovering the fine bone structures were obtained by applying CNNMLAA+NAC. Additionally, the μ-values in the lungs were overestimated by CNNNAC. Activity images (λ) corrected for attenuation using μ-CNNMLAA and μ-CNNMLAA+NAC were superior to those corrected using μ-CNNNAC, in terms of their similarity to λ-CT. However, the improvement in the similarity with λ-CT by combining the CNNNAC and CNNMLAA approaches was insignificant (percent error for lung cancer lesions, λ-CNNNAC = 5.45% ± 7.88%; λ-CNNMLAA = 1.21% ± 5.74%; λ-CNNMLAA+NAC = 1.91% ± 4.78%; percent error for bone cancer lesions, λ-CNNNAC = 1.37% ± 5.16%; λ-CNNMLAA = 0.23% ± 3.81%; λ-CNNMLAA+NAC = 0.05% ± 3.49%). CONCLUSION: The use of CNNNAC was feasible for scatter estimation to address the chicken-egg dilemma in MLAA reconstruction, but CNNMLAA outperformed CNNNAC.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Hwang D, Kang SK, Kim KY, et al. Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography. Eur J Nucl Med Mol Imaging. 2021. PMID: 34882262. doi:10.1007/s00259-021-05637-0

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。