文献速递胸部骨肌技术与安全CT

机器学习在低剂量胸部CT扫描上自动测量椎旁肌面积与衰减值

Machine Learning for Automatic Paraspinous Muscle Area and Attenuation Measures on Low-Dose Chest CT Scans.
PubMed 文献 · Acad Radiol · 2019-07-17

研究开发并评估基于U-Net卷积神经网络的自动分割算法,在1875张单层CT图像上训练、209张国家肺癌筛查试验低剂量胸部CT图像上测试,自动分割T12椎体水平的左侧椎旁肌并测量肌肉横截面积与肌肉衰减值。算法与手工标注的Dice中位数为0.94(标准差0.04),肌肉横截面积与衰减值的相关性分别为r²=0.86和r²=0.95(均p<0.0001)。作者认为该算法在异质性低剂量CT图像上泛化良好,可能用于常规胸部CT自动量化肌肉指标以筛查肌少症。

要点

  • U-Net卷积神经网络在低剂量胸部CT上自动分割左侧椎旁肌,测试集Dice中位数0.94(标准差0.04)。
  • 自动测量与手工标注的肌肉横截面积相关性r²=0.86、肌肉衰减值相关性r²=0.95(均p<0.0001)。
  • 算法在33个临床中心、4个厂商扫描仪获得的异质性低剂量CT图像上泛化良好,作者认为可能用于自动筛查肌少症。

核心结论

  • 基于U-Net的机器学习算法在NLST低剂量胸部CT上测量椎旁肌,与手工标注的参考标准相比结果良好,作者认为该算法可能实现常规胸部CT肌肉指标的自动量化以筛查肌少症。

研究设计与样本

  • 研究为算法开发与评估研究,卷积神经网络基于U-Net架构,在1875张单层CT图像数据集上训练。
  • 测试集为209张国家肺癌筛查试验(NLST)参与者的CT图像,来自33个临床中心、4个厂商的扫描仪,为非增强低剂量胸部CT。
  • 参与者平均年龄71.6岁(范围70-74岁),参考标准为在T12椎体水平手工分割左侧椎旁肌。

诊断标准与关键数值

  • 与手工参考标准分割相比,机器学习算法在测试集的中位Dice评分为0.94(标准差0.04)。
  • 肌肉横截面积均值(标准差):手工参考标准14.3(3.6)cm²,机器学习分割13.7(3.5)cm²。
  • 肌肉衰减值均值(标准差):手工参考标准41.6(7.6)HU,机器学习分割43.5(7.9)HU。
  • 机器学习算法与手工参考标准的相关性:肌肉横截面积r²=0.86(p<0.0001),肌肉衰减值r²=0.95(p<0.0001)。

临床应用与阅片要点

  • 作者认为该算法可能实现常规胸部CT上肌肉指标的自动量化,以筛查肌少症。
  • 原文未据此给出阅片或报告流程的具体推荐。

局限性

  • 原文未报告局限性。

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 develop and evaluate an automated machine learning (ML) algorithm for segmenting the paraspinous muscles on chest computed tomography (CT) scans to evaluate for presence of sarcopenia.

MATERIALS AND METHODS: A convolutional neural network based on the U-Net architecture was trained to perform muscle segmentation on a dataset of 1875 single slice CT images and was tested on 209 CT images of participants in the National Lung Screening Trial. Low-dose, noncontrast CT examinations were obtained at 33 clinical sites, using scanners from four manufacturers. The study participants had a mean age of 71.6 years (range, 70-74 years). Ground truth was obtained by manually segmenting the left paraspinous muscle at the level of the T12 vertebra. Muscle cross-sectional area (CSA) and muscle attenuation (MA) were recorded. Comparison between the ML algorithm and ground truth measures of muscle CSA and MA were obtained using Dice similarity coefficients and Pearson correlations.

RESULTS: Compared to ground truth segmentation, the ML algorithm achieved median (standard deviation) Dice scores of 0.94 (0.04) in the test set. Mean (SD) muscle CSA was 14.3 (3.6) cm2 for ground truth and 13.7 (3.5) cm2 for ML segmentation. Mean (SD) MA was 41.6 (7.6) Hounsfield units (HU) for ground truth and 43.5 (7.9) HU for ML segmentation. There was high correlation between ML algorithm and ground truth for muscle CSA (r2 = 0.86; p < 0.0001) and MA (r2 = 0.95; p < 0.0001).

CONCLUSION: The ML algorithm for measurement of paraspinous muscles compared favorably to manual ground truth measurements in the NLST. The algorithm generalized well to a heterogeneous set of low-dose CT images and may be capable of automated quantification of muscle metrics to screen for sarcopenia on routine chest CT examinations.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Barnard R, Tan J, Roller B, et al. Machine Learning for Automatic Paraspinous Muscle Area and Attenuation Measures on Low-Dose Chest CT Scans. Acad Radiol. 2019. PMID: 31326311. doi:10.1016/j.acra.2019.06.017

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。