文献速递心血管胸部CT

心脏CT中心肌梗死的纹理分析:与视觉分析的比较及迭代重建的影响

Texture analysis of myocardial infarction in CT: Comparison with visual analysis and impact of iterative reconstruction.
PubMed 文献 · Eur J Radiol · 2019-02-27

本研究比较纹理分析与主观视觉诊断在心脏CT中检测慢性心肌梗死的能力,并评估迭代重建的影响。10例确诊慢性心肌梗死患者和20例无心脏异常对照接受相同方案的对比增强心脏CT,重建采用滤波反投影和高级模型迭代重建(强度3-5级)。纹理分析在所有重建下分类正确率94%-97%、AUC 0.94-0.99,但训练/测试分割后最佳仅73%、AUC 0.65;主观视觉分析读者内一致性极好(kappa 0.93)但读者间一致性差(kappa 0.3)。

要点

  • 纹理分析对慢性心肌梗死诊断在所有重建下正确分类94%-97%、AUC 0.94-0.99。
  • 主观视觉分析读者内一致性极好(kappa 0.93),读者间一致性差(kappa 0.3)。
  • 迭代重建对主观和客观图像分析均有相当影响;训练/测试分割后纹理分析最佳为迭代重建5级(正确分类73%、AUC 0.65)。

核心结论

  • 与经验不足读者的主观、不可靠视觉分析相比,纹理分析能对心脏CT中的慢性心肌梗死进行客观、可重复的诊断,准确性更高;迭代重建对主观和客观图像分析均有相当影响。

研究设计与样本

  • 研究纳入10例确诊慢性心肌梗死患者(4例女性,平均年龄68±11岁)和20例无心脏异常对照(8例女性,平均年龄52±11岁),均接受相同方案的对比增强心脏CT;图像采用滤波反投影和高级模型迭代重建(强度3-5级)重建;由三名独立、盲法、经验水平不同的读者进行主观诊断;采用基于机器学习的决策树模型对整个数据集及训练/测试分割后数据进行心肌梗死分类以避免过拟合。

诊断标准与关键数值

  • 主观视觉分析诊断心肌梗死的读者内一致性kappa为0.93,读者间一致性kappa为0.3,且不同图像重建下表现不一。
  • 纹理分析在所有图像重建下正确分类率为94%-97%,曲线下面积为0.94-0.99。
  • 训练/测试数据分割后总体性能较低,最佳结果为迭代重建5级:正确分类率73%,曲线下面积0.65。

局限性

  • 训练/测试数据分割后总体性能较低,最佳结果仅为迭代重建5级正确分类率73%、曲线下面积0.65。

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 compare texture analysis (TA) with subjective visual diagnosis of myocardial infarction (MI) in cardiac computed tomography (CT) and to evaluate the impact of iterative reconstruction (IR).

METHODS: Ten patients (4 women, mean age 68 ± 11 years) with confirmed chronic MI and 20 controls (8 women, mean age 52 ± 11 years) with no cardiac abnormality underwent contrast-enhanced cardiac CT with the same protocol. Images were reconstructed with filtered back projection (FBP) and with advanced modeled IR at strength levels 3-5. Subjective diagnosis of MI was made by three independent, blinded readers with different experience levels. Classification of MI was performed using machine learning-based decision tree models for the entire data set and after splitting into training and test data to avoid overfitting.

RESULTS: Subjective visual analysis for diagnosis of MI showed excellent intrareader (kappa: 0.93) but poor interreader agreement (kappa: 0.3), with variable performance at different image reconstructions. TA showed high performance for all image reconstructions (correct classifications: 94%-97%, areas under the curve: 0.94-0.99). After splitting into training and test data, overall lower performances were observed, with best results for IR at level 5 (correct classifications: 73%, area under the curve: 0.65).

CONCLUSIONS: As compared with subjective, nonreliable visual analysis of inexperienced readers, TA enables objective and reproducible diagnosis of chronic MI in cardiac CT with higher accuracy. IR has a considerable impact on both subjective and objective image analysis.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Mannil M, von Spiczak J, Muehlematter UJ, et al. Texture analysis of myocardial infarction in CT: Comparison with visual analysis and impact of iterative reconstruction. Eur J Radiol. 2019. PMID: 30927955. doi:10.1016/j.ejrad.2019.02.037

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。