文献速递心血管外周血管CT

基于深度学习算法在平扫CT上检测主动脉夹层

Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT.
PubMed 文献 · Eur Radiol · 2020-08-28

本研究纳入170例患者(85例主动脉夹层,85例无夹层),开发基于Xception架构卷积神经网络的主动脉夹层检测算法,使用平扫CT图像训练和测试。算法AUC为0.940,取阈值0.400时准确度90.0%、敏感度91.8%、特异度88.2%,与5名放射科医师的平均表现无显著差异(p > 0.05),提示该算法可能辅助临床实践以减少主动脉夹层漏诊。

要点

  • 算法在平扫CT上检测主动脉夹层的AUC为0.940,阈值0.400时准确度90.0%、敏感度91.8%、特异度88.2%。
  • 5名放射科医师的准确度、敏感度、特异度中位数分别为88.8%、90.6%、94.1%,算法与医师平均表现无显著差异(p > 0.05)。
  • 作者认为该算法与放射科医师诊断表现相当,可能通过减少漏诊来支持临床实践。

核心结论

  • 开发的深度学习算法在检测主动脉夹层方面与放射科医师诊断表现相当,提示该方法可能通过减少漏诊来支持临床实践。

研究设计与样本

  • 研究纳入170例患者,其中85例有主动脉夹层、85例无主动脉夹层。
  • 使用Xception架构的卷积神经网络开发主动脉夹层检测算法,80%患者数据用于训练和验证、20%用于测试,并进行五折交叉验证。
  • 训练共使用平均6688幅平扫CT图像(层厚5 mm)。
  • 一名放射科医师审阅增强和平扫CT图像并识别主动脉夹层层面,作为参考标准(ground truth)。
  • 5名放射科医师独立评估图像,比较算法与医师的准确度、敏感度和特异度。

诊断标准与关键数值

  • 算法检测主动脉夹层的AUC为0.940。
  • 取 cutoff 值0.400时,算法准确度90.0%、敏感度91.8%、特异度88.2%。
  • 放射科医师的准确度中位数(范围)为88.8%(83.5-94.1)%、敏感度90.6%(83.5-94.1)%、特异度94.1%(72.9-97.6)%。
  • 算法与放射科医师平均表现之间在准确度、敏感度或特异度方面均无显著差异(p > 0.05)。

临床应用与阅片要点

  • 作者认为该算法与放射科医师诊断表现相当,可能通过减少漏诊来支持临床实践。

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

OBJECTIVES: To develop a deep learning-based algorithm to detect aortic dissection (AD) and evaluate the diagnostic ability of the algorithm compared with those of radiologists.

METHODS: Included in the study were 170 patients (85 with AD and 85 without AD). An AD detection algorithm was developed using a convolutional neural network with Xception architecture. Of the patient data, 80% were used for training and validation and 20% were used for testing. Fivefold cross-validation was performed to evaluate the method. An average of 6688 non-contrast-enhanced CT images (slice thickness, 5 mm) were used for training. A radiologist reviewed both contrast-enhanced and non-contrast-enhanced images and identified the slices of AD. The identified slices were used as ground truth. Receiver operating characteristic curve and area under the curve (AUC) analysis was performed. Five radiologists independently evaluated the images. The accuracy, sensitivity, and specificity of the algorithm and those of the radiologists were compared.

RESULTS: The AUC of the developed algorithm was 0.940, and a cutoff value of 0.400 provided accuracy of 90.0%, sensitivity of 91.8%, and specificity of 88.2%. For the radiologists, median (range) accuracy, sensitivity, and specificity were 88.8 (83.5-94.1)%, 90.6 (83.5-94.1)%, and 94.1 (72.9-97.6)%, respectively. There was no significant difference in performance in terms of accuracy, sensitivity, or specificity between the algorithm and the average performance of the radiologists (p > 0.05).

CONCLUSIONS: The developed algorithm showed comparable diagnostic performance to radiologists for detecting AD, which suggests the potential of the proposed method to support clinical practice by reducing missed ADs.

KEY POINTS: • A deep learning-based algorithm for detecting aortic dissection was developed using the non-contrast-enhanced CT images of 170 patients. • The algorithm had an AUC of 0.940 for detecting aortic dissection. • The accuracy, sensitivity, and specificity of the algorithm were comparable to those of radiologists.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Hata A, Yanagawa M, Yamagata K, et al. Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT. Eur Radiol. 2020. PMID: 32857203. doi:10.1007/s00330-020-07213-w

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。