文献速递胸部CT

疫情期间定制COVID-19影像分析工具的开发和临床实施:开放式临床嵌入式软件开发平台与机器学习的协同效应

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning.
PubMed 文献 · Eur J Radiol · 2020-08-28

在COVID-19疫情期间,某放射科在10天内基于临床嵌入式软件平台开发并部署了胸部CT肺分割与磨玻璃影量化自动工具。算法在独立测试子集(N=66)上与外部算法比较,内部算法低估程度为1.8%且不依赖总磨玻璃影负荷,肺分割Dice系数达0.97,达到类人水平。

要点

  • 基于临床嵌入式平台与深度学习,10天内完成胸部CT肺分割和磨玻璃影量化工具的开发与临床部署。
  • 内部算法肺分割Dice系数0.97,达到类人水平;磨玻璃影量化低估1.8%且不依赖总负荷,更适合随访。
  • 外部算法磨玻璃影量化低估0.9%,但低估程度依赖总磨玻璃影负荷。

核心结论

  • 机器学习与临床嵌入式软件开发平台结合,实现了省时开发、即时部署和临床常规快速采纳。
  • 所开发的肺分割与磨玻璃影量化算法在10天内即达到临床可用状态,在复杂病例中也达到类人水平。

研究设计与样本

  • 研究类型为算法开发与临床实施研究,使用半自动和人工创建的金标准训练深度卷积神经网络算法,金标准总样本量Ntotal=172。
  • 在独立测试子集(N=66)上比较内部算法与外部开发算法的性能。

关键影像表现/征象

  • 内部算法肺分割Dice系数为0.97,达到类人水平。
  • 磨玻璃影量化方面,内部算法低估1.8%,外部算法低估0.9%。
  • 内部算法的低估程度不依赖总磨玻璃影负荷,而外部参考算法低估程度依赖总磨玻璃影负荷。

诊断标准与关键数值

  • 肺分割性能以Dice系数评估,内部算法为0.97。
  • 磨玻璃影量化以低估百分比评估,内部算法低估1.8%,外部算法低估0.9%。

临床应用与阅片要点

  • 内部算法因低估程度不依赖总磨玻璃影负荷,更适合用于随访。
  • 算法在10天内完成开发并部署至临床常规,可用于胸部CT肺分割和磨玻璃影量化。

局限性

  • 内部算法在磨玻璃影量化上存在1.8%的低估,外部算法存在0.9%的低估。
  • 外部算法低估程度依赖总磨玻璃影负荷,内部算法则不依赖。

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: During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic.

METHOD: Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (Ntotal = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66).

RESULTS: The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up.

CONCLUSIONS: The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Anastasopoulos C, Weikert T, Yang S, et al. Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning. Eur J Radiol. 2020. PMID: 32927416. doi:10.1016/j.ejrad.2020.109233

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。