文献速递胸部CT

基于深度学习的胸部CT气胸快速筛查系统

Deep learning-enabled system for rapid pneumothorax screening on chest CT.
PubMed 文献 · Eur J Radiol · 2019-09-26

本研究开发并评估了一种基于深度学习的图像分类程序,用于在胸部CT上检测气胸。该程序在80例胸部CT上训练,并在200例独立测试集上验证,受试者层面敏感度为100%(160/160例气胸全部检出),特异度为82.5%(33/40例真阴性)。结论认为该程序在自动检测胸部CT气胸方面表现出高准确度,可用于快速预筛大量病例。

要点

  • 该深度学习程序在独立测试集上受试者层面敏感度100%(160/160),特异度82.5%(33/40)。
  • 假阳性分类主要与测试图像中的肺气肿和/或伪影有关。
  • 作者认为该方法可用于快速预筛大量病例中的气胸这一关键发现。

核心结论

  • 基于深度学习的程序在胸部CT自动检测气胸方面表现出高准确度。
  • 作者认为通过在高性能计算平台上实施并将放射科医生的领域知识整合到分析框架中,该方法可用于快速预筛大量病例中的气胸。

研究设计与样本

  • 研究经IRB批准,使用恒定大小(36*36像素)的2D图像块训练了一个八层卷积神经网络(CNN)。
  • 训练集为80例胸部CT,其中50例有气胸、30例无气胸。
  • 图像块根据代表气胸的概率进行分类,随后生成3D热图;热图进一步定义包括气胸面积大小、区域相对于肺边界的相对位置以及基于区域各向异性的形状描述符,并训练支持向量机(SVM)进行分类。
  • 在独立的200例胸部CT测试数据集上评估程序性能,其中160/200(75%)有气胸、40/200(25%)无气胸。

关键影像表现/征象

  • 假阳性分类主要与测试图像中的肺气肿和/或伪影有关。

诊断标准与关键数值

  • 在200例测试集上,受试者层面敏感度为100%(160/160例气胸全部检出),特异度为82.5%(33/40例真阴性)。

局限性

  • 假阳性分类主要与测试图像中的肺气肿和/或伪影有关。

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: Prompt diagnosis and quantitation of pneumothorax impact decisions pertaining to patient management. The purpose of our study was to develop and evaluate the accuracy of a deep learning (DL)-based image classification program for detection of pneumothorax on chest CT.

METHOD: In an IRB approved study, an eight-layer convolutional neural network (CNN) using constant-size (36*36 pixels) 2D image patches was trained on a set of 80 chest CTs, with (n = 50) and without (n = 30) pneumothorax. Image patches were classified based on their probability of representing pneumothorax with subsequent generation of 3D heat-maps. The heat maps were further defined to include 1) pneumothorax area size, 2) relative location of the region to the lung boundary, and 3) a shape descriptor based on regional anisotropy. A support vector machine (SVM) was trained for classification.

RESULT: We assessed performance of our program in a separate test dataset of 200 chest CT examinations, with (160/200, 75%) and without (40/200, 25%) pneumothorax. Data were analyzed to determine the accuracy, sensitivity, specificity. The subject-wise sensitivity was 100% (all 160/160 pneumothoraces detected) and specificity was 82.5% (33 true negative/40). False positive classifications were primarily related to emphysema and/or artifacts in the test images.

CONCLUSION: This deep learning-based program demonstrated high accuracy for automatic detection of pneumothorax on chest CTs. By implementing it on a high-performance computing platform and integrating the domain knowledge of radiologists into the analytics framework, our method can be used to rapidly pre-screen large numbers of cases for presence of pneumothorax, a critical finding.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Li X, Thrall JH, Digumarthy SR, et al. Deep learning-enabled system for rapid pneumothorax screening on chest CT. Eur J Radiol. 2019. PMID: 31585302. doi:10.1016/j.ejrad.2019.108692

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。