文献速递心血管US

基于超声心动图图像评估区域性室壁运动异常的深度学习方法

A Deep Learning Approach for Assessment of Regional Wall Motion Abnormality From Echocardiographic Images.
PubMed 文献 · JACC Cardiovasc Imaging · 2019-05-15

本研究纳入300例有心肌梗死病史的患者(左前降支、左回旋支、右冠状动脉梗死各100例)和100例年龄匹配的正常对照,利用深度卷积神经网络(DCNN)从二维超声心动图图像中检测区域性室壁运动异常(RWMA)并区分梗死区域。DCNN检测RWMA的AUC与心脏科医生和超声技师读者相似(0.99 vs 0.98,p=0.15),显著高于住院医师读者(0.99 vs 0.90,p=0.002);区分RWMA区域的AUC与心脏科医生和超声技师读者相似(0.97 vs 0.95,p=0.61),显著高于住院医师读者(0.97 vs 0.83,p=0.003);在独立站点验证组(n=40)中AUC为0.90。结论支持DCNN用于超声心动图领域RWMA自动化诊断的可能性。

要点

  • DCNN检测RWMA的AUC为0.99,与心脏科医生和超声技师读者(0.98)相似,显著高于住院医师读者(0.90)。
  • DCNN区分梗死区域的AUC为0.97,与心脏科医生和超声技师读者(0.95)相似,显著高于住院医师读者(0.83)。
  • 独立站点验证组(n=40)中DCNN的AUC为0.90。

核心结论

  • 结果支持DCNN用于超声心动图领域RWMA自动化诊断的可能性。

研究设计与样本

  • 研究纳入300例有心肌梗死病史的患者(左前降支、左回旋支、右冠状动脉梗死各100例)和100例年龄匹配的正常对照;每个病例包含短轴切面舒张末期、收缩中期和收缩末期的超声心动图图像;DCNN经过100步训练后,在测试集上计算诊断准确率,并独立训练10个相同模型版本进行集成预测;另在独立站点验证组(n=40)中评估。

关键影像表现/征象

  • 检测WMAs存在与否时,深度学习算法的AUC为0.99,心脏科医生和超声技师读者为0.98,住院医师读者为0.90。
  • 检测WMAs区域时,深度学习算法的AUC为0.97,心脏科医生和超声技师读者为0.95,住院医师读者为0.83。
  • 在独立站点验证组(n=40)中,深度学习算法的AUC为0.90。

诊断标准与关键数值

  • 检测WMAs存在与否:深度学习算法AUC 0.99 vs 心脏科医生和超声技师读者0.98(p=0.15),深度学习算法AUC 0.99 vs 住院医师读者0.90(p=0.002)。
  • 检测WMAs区域:深度学习算法AUC 0.97 vs 心脏科医生和超声技师读者0.95(p=0.61),深度学习算法AUC 0.97 vs 住院医师读者0.83(p=0.003)。
  • 独立站点验证组(n=40):深度学习算法AUC为0.90。

临床应用与阅片要点

  • DCNN可能用于超声心动图领域RWMA的自动化诊断。

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: This study investigated whether a deep convolutional neural network (DCNN) could provide improved detection of regional wall motion abnormalities (RWMAs) and differentiate among groups of coronary infarction territories from conventional 2-dimensional echocardiographic images compared with that of cardiologists, sonographers, and resident readers.

BACKGROUND: An effective intervention for reduction of misreading of RWMAs is needed. The hypothesis was that a DCNN trained using echocardiographic images would provide improved detection of RWMAs in the clinical setting.

METHODS: A total of 300 patients with a history of myocardial infarction were enrolled. From this cohort, 3 groups of 100 patients each had infarctions of the left anterior descending (LAD) artery, the left circumflex (LCX) branch, and the right coronary artery (RCA). A total of 100 age-matched control patients with normal wall motion were selected from a database. Each case contained cardiac ultrasonographs from short-axis views at end-diastolic, mid-systolic, and end-systolic phases. After the DCNN underwent 100 steps of training, diagnostic accuracies were calculated from the test set. Independently, 10 versions of the same model were trained, and ensemble predictions were performed using those versions.

RESULTS: For detection of the presence of WMAs, the area under the receiver-operating characteristic curve (AUC) produced by the deep learning algorithm was similar to that produced by the cardiologists and sonographer readers (0.99 vs. 0.98, respectively; p = 0.15) and significantly higher than the AUC result of the resident readers (0.99 vs. 0.90, respectively; p = 0.002). For detection of territories of WMAs, the AUC by the deep learning algorithm was similar to the AUC by the cardiologist and sonographer readers (0.97 vs. 0.95, respectively; p = 0.61) and significantly higher than the AUC by resident readers (0.97 vs. 0.83, respectively; p = 0.003). From a validation group at an independent site (n = 40), the AUC by the deep learning algorithm was 0.90.

CONCLUSIONS: The present results support the possibility of using DCNN for automated diagnosis of RWMAs in the field of echocardiography.

来源:JACC Cardiovasc Imaging,查看原文。版权归原作者所有。

引用

  1. Kusunose K, Abe T, Haga A, et al. A Deep Learning Approach for Assessment of Regional Wall Motion Abnormality From Echocardiographic Images. JACC Cardiovasc Imaging. 2019. PMID: 31103590. doi:10.1016/j.jcmg.2019.02.024

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。