文献速递胸部技术与安全CT

更深U-Net的卷积神经网络用于稀疏视图CT重建的定量与定性评价

Quantitative and Qualitative Evaluation of Convolutional Neural Networks with a Deeper U-Net for Sparse-View Computed Tomography Reconstruction.
PubMed 文献 · Acad Radiol · 2019-07-04

基于U-Net残差学习、含四个收缩与扩张路径的既往网络与含八个路径的提出网络相比,提出网络在定量和定性上均显著更优,总体图像质量四分位距为3.0-3.5对1.0-1.0(P<0.001)。但用于肺气肿评价的22例中仅2例平均评分≥2分(3分制),肺气肿表现的可重复性差应予以注意。

要点

  • 增加U-Net收缩与扩张路径可提升稀疏视图CT重建的定量与定性图像质量。
  • 提出网络总体图像质量四分位距3.0-3.5,优于既往网络1.0-1.0(P<0.001)。
  • 肺气肿表现的可重复性差,22例中仅2例平均评分≥2分(3分制)。

核心结论

  • 增加收缩与扩张路径可能有助于基于卷积神经网络的稀疏视图CT重建,但肺气肿表现的可重复性差也应予以注意。

研究设计与样本

  • 本研究为卷积神经网络评价研究,使用公共数据库「The Cancer Imaging Archive」中60例匿名胸部CT病例。
  • 模拟20倍欠采样的稀疏视图CT图像,训练两种卷积神经网络从稀疏视图CT生成去噪图像。
  • 比较基于U-Net残差学习、含四个收缩与扩张路径的既往网络与含八个收缩与扩张路径的提出网络,定量指标为峰值信噪比和结构相似性指数,定性指标为两名放射科医生对解剖可见性、伪影与噪声及总体图像质量的评分,采用Wilcoxon符号秩检验。
  • 另对结节和肺气肿表现进行定性评价。

关键影像表现/征象

  • 提出网络在定量和定性上均显著优于既往网络,总体图像质量四分位距为3.0-3.5对1.0-1.0(P<0.001)。
  • 用于肺气肿评价的22例中仅2例平均评分≥2分(3分制),肺气肿表现可重复性差。

诊断标准与关键数值

  • 定性评价采用两名放射科医生对解剖可见性、伪影与噪声及总体图像质量进行评分,总体图像质量以四分位距报告。
  • 肺气肿评价采用3分制,平均评分≥2分视为可接受,22例中仅2例达到。

临床应用与阅片要点

  • 阅片时应关注稀疏视图CT重建后肺气肿表现的可重复性差,报告肺气肿时需谨慎。

局限性

  • 用于肺气肿评价的22例中仅2例平均评分≥2分(3分制),肺气肿表现的可重复性差。

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: To evaluate the utility of a convolutional neural network (CNN) with an increased number of contracting and expanding paths of U-net for sparse-view CT reconstruction.

MATERIALS AND METHODS: This study used 60 anonymized chest CT cases from a public database called "The Cancer Imaging Archive". Eight thousand images from 40 cases were used for training. Eight hundred and 80 images from another 20 cases were used for quantitative and qualitative evaluation, respectively. Sparse-view CT images subsampled by a factor of 20 were simulated, and two CNNs were trained to create denoised images from the sparse-view CT. A CNN based on U-net with residual learning with four contracting and expanding paths (the preceding CNN) was compared with another CNN with eight contracting and expanding paths (the proposed CNN) both quantitatively (peak signal to noise ratio, structural similarity index), and qualitatively (the scores given by two radiologists for anatomical visibility, artifact and noise, and overall image quality) using the Wilcoxon signed-rank test. Nodule and emphysema appearance were also evaluated qualitatively.

RESULTS: The proposed CNN was significantly better than the preceding CNN both quantitatively and qualitatively (overall image quality interquartile range, 3.0-3.5 versus 1.0-1.0 reported from the preceding CNN; p < 0.001). However, only 2 of 22 cases used for emphysematous evaluation (2 CNNs for every 11 cases with emphysema) had an average score of ≥ 2 (on a 3 point scale).

CONCLUSION: Increasing contracting and expanding paths may be useful for sparse-view CT reconstruction with CNN. However, poor reproducibility of emphysema appearance should also be noted.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Nakai H, Nishio M, Yamashita R, et al. Quantitative and Qualitative Evaluation of Convolutional Neural Networks with a Deeper U-Net for Sparse-View Computed Tomography Reconstruction. Acad Radiol. 2019. PMID: 31281082. doi:10.1016/j.acra.2019.05.016

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。