文献速递神经外周血管US

基于卷积图像特征的颈动脉彩色多普勒评估缺血性卒中

Assessing Ischemic Stroke with Convolutional Image Features in Carotid Color Doppler.
PubMed 文献 · Ultrasound Med Biol · 2021-05-15

回顾性分析106例急性缺血性卒中患者549幅与79名正常对照483幅颈动脉彩色多普勒图像,以两名神经放射科医师共识为金标准,用10折交叉验证评估CNN模型。从头训练的AlexNet准确率91.67%、敏感度93.33%、特异度90.20%、AUC 0.9432;迁移学习模型准确率77.69%–83.94%;绿色通道准确率87.50%、敏感度97.78%、特异度78.43%、AUC 0.9507。

要点

  • 从头训练的AlexNet对颈动脉彩色多普勒图像识别缺血性卒中的准确率为91.67%,AUC为0.9432。
  • 绿色通道单独诊断敏感度97.78%、特异度78.43%、AUC 0.9507,特异度低于AlexNet的90.20%。
  • 迁移学习模型准确率77.69%–83.94%,低于从头训练AlexNet的91.67%。

核心结论

  • 所提出的CNN架构作为计算机辅助诊断系统,提示可从颈动脉彩色多普勒图像自动提取特征预测缺血性卒中,并有可能在临床使用中提供诊断建议。

研究设计与样本

  • 回顾性分析106例急性缺血性卒中患者549幅和79名正常对照483幅共1032幅颈动脉彩色多普勒图像,以两名神经放射科医师共识为金标准,采用10折交叉验证评估不同CNN模型(含与不含迁移学习)。

诊断标准与关键数值

  • 从头训练AlexNet准确率91.67%、敏感度93.33%、特异度90.20%、AUC 0.9432;其他迁移学习模型准确率77.69%–83.94%;绿色通道准确率87.50%、敏感度97.78%、特异度78.43%、AUC 0.9507。

临床应用与阅片要点

  • 作者认为该CNN架构作为计算机辅助诊断系统,提示可从颈动脉彩色多普勒图像自动提取特征预测缺血性卒中。
  • 作者认为该方案有可能在临床使用中提供诊断建议。

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

Stroke is a leading cause of disability and death worldwide. Early and accurate recognition of acute stroke is critical for achieving a good prognosis. The novel automated system proposed in this study was based on convolutional neural networks (CNNs), which were used to identify lesion findings on carotid color Doppler (CCD) images in patients with acute ischemic stroke. An image database composed of 1032 CCD images from 106 patients with acute ischemic stroke (549 images) and from 79 normal controls (483 images) was retrospectively analyzed. Taking the consensus of two neuroradiologists as the gold standard, different CNN models with and without transfer learning were evaluated with 10-fold cross-validation. The diagnostic information provided from individual color channels was also explored. AlexNet, which was trained from scratch, achieved an accuracy of 91.67%, a sensitivity of 93.33%, a specificity of 90.20% and an area under the receiver operating characteristic curves (AUC) of 0.9432. Other transferred models achieved accuracies between 77.69% and 83.94%. In channel comparisons, the green channel had the best performance, with an accuracy of 87.50%, a sensitivity of 97.78%, a specificity of 78.43% and an AUC of 0.9507. The proposed CNN architecture, as a computer-aided diagnosis system, suggests using automatic feature extraction from CCD images to predict ischemic stroke. The developed scheme has the potential to provide diagnostic suggestions in clinical use.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Lo CM, Hung PH. Assessing Ischemic Stroke with Convolutional Image Features in Carotid Color Doppler. Ultrasound Med Biol. 2021. PMID: 34001404. doi:10.1016/j.ultrasmedbio.2021.03.038

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。