文献速递腹部技术与安全CT

腹部肌肉与脂肪CT图像分割深度学习系统的开发与验证

Development and Validation of a Deep Learning System for Segmentation of Abdominal Muscle and Fat on Computed Tomography.
PubMed 文献 · Korean J Radiol · 2020-01-01

本研究开发并验证了一种基于全卷积网络的深度学习系统,用于在CT图像上全自动分割腹部肌肉和脂肪面积。系统在内部验证集(426次CT扫描)和外部验证集(171次CT扫描)上均表现出高Dice相似系数(肌肉0.96-0.97,皮下脂肪0.97,内脏脂肪0.97)和低横截面积误差(肌肉1.8%-2.7%,皮下脂肪3.8%-4.6%,内脏脂肪1.8%-2.3%)。结论认为该系统在腹部肌肉和脂肪自动分割方面具有高性能和准确性。

要点

  • 系统在L3椎体下终板层面轴位CT上自动分割骨骼肌、内脏脂肪和皮下脂肪。
  • 内部验证集Dice相似系数:肌肉0.96、皮下脂肪0.97、内脏脂肪0.97。
  • 外部验证集Dice相似系数均为0.97,横截面积误差均低于5%。

核心结论

  • 基于全卷积网络的分割系统在CT图像上自动分割腹部肌肉和脂肪表现出高性能和准确性。

研究设计与样本

  • 开发并验证基于全卷积网络的深度学习分割系统,训练集为467名受试者的883次CT扫描。
  • 分析层面为第3腰椎下终板水平的轴位CT图像,手动绘制的骨骼肌、内脏脂肪和皮下脂肪分割图作为参考标准。
  • 内部验证集为308名受试者的426次CT扫描,外部验证集为两家外院171名受试者的171次CT扫描。

诊断标准与关键数值

  • 内部验证集平均Dice相似系数:肌肉0.96、皮下脂肪0.97、内脏脂肪0.97;平均横截面积误差:肌肉2.1%、皮下脂肪3.8%、内脏脂肪1.8%。
  • 外部验证集平均Dice相似系数:肌肉0.97、皮下脂肪0.97、内脏脂肪0.97;平均横截面积误差:肌肉2.7%、皮下脂肪4.6%、内脏脂肪2.3%。

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

OBJECTIVE: We aimed to develop and validate a deep learning system for fully automated segmentation of abdominal muscle and fat areas on computed tomography (CT) images.

MATERIALS AND METHODS: A fully convolutional network-based segmentation system was developed using a training dataset of 883 CT scans from 467 subjects. Axial CT images obtained at the inferior endplate level of the 3rd lumbar vertebra were used for the analysis. Manually drawn segmentation maps of the skeletal muscle, visceral fat, and subcutaneous fat were created to serve as ground truth data. The performance of the fully convolutional network-based segmentation system was evaluated using the Dice similarity coefficient and cross-sectional area error, for both a separate internal validation dataset (426 CT scans from 308 subjects) and an external validation dataset (171 CT scans from 171 subjects from two outside hospitals).

RESULTS: The mean Dice similarity coefficients for muscle, subcutaneous fat, and visceral fat were high for both the internal (0.96, 0.97, and 0.97, respectively) and external (0.97, 0.97, and 0.97, respectively) validation datasets, while the mean cross-sectional area errors for muscle, subcutaneous fat, and visceral fat were low for both internal (2.1%, 3.8%, and 1.8%, respectively) and external (2.7%, 4.6%, and 2.3%, respectively) validation datasets.

CONCLUSION: The fully convolutional network-based segmentation system exhibited high performance and accuracy in the automatic segmentation of abdominal muscle and fat on CT images.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Park HJ, Shin Y, Park J, et al. Development and Validation of a Deep Learning System for Segmentation of Abdominal Muscle and Fat on Computed Tomography. Korean J Radiol. 2020. PMID: 31920032. doi:10.3348/kjr.2019.0470

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。