文献速递腹部技术与安全CT

基于深度学习的CT图像腹部皮下与内脏脂肪体积定量

Deep Learning-based Quantification of Abdominal Subcutaneous and Visceral Fat Volume on CT Images.
PubMed 文献 · Acad Radiol · 2020-08-06

研究开发基于U-Net架构的深度学习算法,用模板数据增强策略以少量训练图像测量腹部CT脂肪。在3例连续层面和100例随机图像上评估,自动与手动分割总体Dice系数0.94,皮下与内脏脂肪体积相关系数均为0.99,自动分割约1分钟完成555层,手动约46小时。

要点

  • 自动与手动分割总体Dice系数0.94,皮下和内脏脂肪体积相关系数均为0.99。
  • 自动分割555层CT约需1分钟,手动分割约需46小时。
  • 模板数据增强使少量训练图像即可实现腹部皮下与内脏脂肪的准确快速定量。

核心结论

  • 利用模板数据增强策略的深度学习方法可用少量训练图像准确、快速地定量全腹部皮下脂肪和内脏脂肪。

研究设计与样本

  • 研究为算法开发与评估研究,采用U-Net架构的深度学习算法在CT图像上测量腹部脂肪。
  • 训练集来自7例受试者腹部连续CT图像的手动分割皮下脂肪和内脏脂肪,并用模板数据增强生成训练数据。
  • 测试集包括3例受试者的连续CT层面和100例受试者上、中、下腹部随机选取的CT图像,测试共使用555层CT。
  • 参考标准为手动分割的皮下脂肪和内脏脂肪。

诊断标准与关键数值

  • 自动与手动分割的总体Dice相似系数为0.94。
  • 两种方法定量的皮下脂肪体积Pearson相关系数为0.99,内脏脂肪体积Pearson相关系数为0.99。
  • 两种方法定量的皮下脂肪总体百分残差平方误差为5.5%,内脏脂肪为8.5%。

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: Develop a deep learning-based algorithm using the U-Net architecture to measure abdominal fat on computed tomography (CT) images.

MATERIALS AND METHODS: Sequential CT images spanning the abdominal region of seven subjects were manually segmented to calculate subcutaneous fat (SAT) and visceral fat (VAT). The resulting segmentation maps of SAT and VAT were augmented using a template-based data augmentation approach to create a large dataset for neural network training. Neural network performance was evaluated on both sequential CT slices from three subjects and randomly selected CT images from the upper, central, and lower abdominal regions of 100 subjects.

RESULTS: Both subcutaneous and abdominal cavity segmentation images created by the two methods were highly comparable with an overall Dice similarity coefficient of 0.94. Pearson's correlation coefficients between the subcutaneous and visceral fat volumes quantified using the two methods were 0.99 and 0.99 and the overall percent residual squared error were 5.5% and 8.5%. Manual segmentation of SAT and VAT on the 555 CT slices used for testing took approximately 46 hours while automated segmentation took approximately 1 minute.

CONCLUSION: Our data demonstrates that deep learning methods utilizing a template-based data augmentation strategy can be employed to accurately and rapidly quantify total abdominal SAT and VAT with a small number of training images.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Grainger AT, Krishnaraj A, Quinones MH, et al. Deep Learning-based Quantification of Abdominal Subcutaneous and Visceral Fat Volume on CT Images. Acad Radiol. 2020. PMID: 32771313. doi:10.1016/j.acra.2020.07.010

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。