文献速递腹部技术与安全CT

结合定量光谱探测器CT与深度学习图像分割评估身体成分

Evaluating body composition by combining quantitative spectral detector computed tomography and deep learning-based image segmentation.
PubMed 文献 · Eur J Radiol · 2020-07-12

本研究开发并评估一款软件工具包,利用双能CT定量信息与深度卷积神经网络分割,在对比增强腹部CT上全自动完成身体成分分析。自动化分类器提取感兴趣层面的准确率达98.7%,皮下脂肪分割平均Dice相似系数0.95,重复检查患者(n=48)中肌肉与皮下脂肪的CCC均为0.99、内脏脂肪为0.98,与BIA同步检查患者(n=39)的线性回归和Bland-Altman分析提示一致性良好(r²为0.67–0.88)。

要点

  • 深度卷积神经网络联合定量阈值分割可从全身体扫描中自动提取腹部层面,准确率98.7%。
  • 重复检查患者(n=48)中肌肉与皮下脂肪CCC均为0.99、内脏脂肪为0.98。
  • 与BIA同步检查患者(n=39)的r²为0.67–0.88,提示一致性良好。

核心结论

  • 联合深度卷积神经网络与阈值分割的光谱探测器CT软件工具包可对身体成分进行准确分析。

研究设计与样本

  • 研究使用公开和私有数据集训练与验证深度卷积神经网络。
  • 采用两个深度卷积神经网络联合定量阈值化,将轴位CT层面分类至腹部区域、将体素分类为脂肪与肌肉并区分皮下与内脏脂肪。
  • 验证纳入接受重复检查(±21天)的患者及同步接受生物电阻抗分析(BIA)的患者。
  • 统计方法包括一致性相关系数(CCC)、线性回归和Bland-Altman分析。

诊断标准与关键数值

  • 自动化分类器从全身体扫描中提取感兴趣层面的准确率为98.7%。
  • 基于深度卷积神经网络的皮下脂肪分割平均Dice相似系数为0.95。
  • 重复检查患者(n=48)中肌肉与皮下脂肪的CCC均为0.99,内脏脂肪为0.98。
  • 与BIA同步检查患者(n=39)的线性回归和Bland-Altman分析提示一致性良好(r²为0.67–0.88)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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

PURPOSE: Aim of this study was to develop and evaluate a software toolkit, which allows for a fully automated body composition analysis in contrast enhanced abdominal computed tomography leveraging the strengths of both, quantitative information from dual energy computed tomography and simple detection and segmentation tasks performed by deep convolutional neuronal networks (DCNN).

METHODS AND MATERIALS: Both, public and private datasets were used to train and validate DCNN. A combination of two DCNN and quantitative thresholding was used to classify axial CT slices to the abdominal region, classify voxels as fat and muscle and to differentiate between subcutaneous and visceral fat. For validation, patients undergoing repetitive examination (±21 days) and patients who underwent concurrent bioelectrical impedance analysis (BIA) were analyzed. Concordance correlation coefficient (CCC), linear regression and Bland-Altman-Analysis were used as statistical tests.

RESULTS: Results provided from the algorithm toolkit were visually validated. The automated classifier was able to extract slices of interest from the full body scans with an accuracy of 98.7 %. DCNN-based segmentation for subcutaneous fat reached a mean dice similarity coefficient of 0.95. CCCs were 0.99 for both muscle and subcutaneous fat and 0.98 for visceral fat in patients undergoing repetitive examinations (n = 48). Further linear regression and Bland-Altman-Analyses suggested good agreement (r2:0.67-0.88) between the software toolkit and patients who underwent concurrent BIA (n = 39).

CONCLUSION: We describe a software toolkit allowing for an accurate analysis of body composition utilizing a combination of DCNN- and threshold-based segmentations from spectral detector computed tomography.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zopfs D, Bousabarah K, Lennartz S, et al. Evaluating body composition by combining quantitative spectral detector computed tomography and deep learning-based image segmentation. Eur J Radiol. 2020. PMID: 32717577. doi:10.1016/j.ejrad.2020.109153

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。