Machine Learning-Based Three-Dimensional Echocardiographic Quantification of Right Ventricular Size and Function: Validation Against Cardiac Magnetic Resonance
Machine Learning-Based Three-Dimensional Echocardiographic Quantification of Right Ventricular Size and Function: Validation Against Cardiac Magnetic Resonance
复制标题
DOI：
10.1016/j.echo.2019.04.001
复制
发表时间：
2019-08-01
影响因子：
6.5
通讯作者：
Lang, Roberto M.
中科院分区：
文献类型：
--
作者：
Genovese, Davide;Rashedi, Nina;Lang, Roberto M.
背景：三维超声心动图（3DE）可以准确和可重复地测量右心室（RV）的大小和功能。然而，3DE在常规临床实践中的广泛实施是有限的，因为现有的软件包相对耗时和技能要求。本研究的目的是测试的准确性和再现性的新机器学习（ML）为基础的，全自动软件的三维定量RV的大小和functions.Methods：五十六心脏病患者的RV大小和功能和图像质量的范围很广，指临床心脏磁共振（CMR）成像，在同一天进行了经胸3DE检查。采用ML算法测量左室收缩末期、舒张末期容积（ESV、EDV）和射血分数（EF），并与CMR参考值进行Bland-Altman和线性回归分析。自动方法在32%的患者中准确，分析时间为15 +/- 1秒，可重复性为100%。在其余68%的患者中，在自动化后处理后需要进行Endothelin轮廓编辑，将分析时间延长至114 +/- 71秒。通过这些最小的调整，与CMR参考值相比，RV体积和EF测量值是准确的（偏差：EDV，-25.6 +/- 21.1 mL; ESV，-7.4 +/- 16 mL; EF，-3.3% +/- 5.2%），并显示出优异的再现性，所有测量的变异系数= 0.95。新的基于ML的3DE算法在三分之一的二尖瓣狭窄患者中提供了准确且完全可重现的RV容积和EF测量值，无需任何边界编辑。在剩下的患者中，快速的最小编辑导致了相当准确的测量结果，具有良好的再现性。这种方法为RV大小和功能的快速三维定量提供了一种很有前途的解决方案。
Background: Three-dimensional echocardiography (3DE) allows accurate and reproducible measurements of right ventricular (RV) size and function. However, widespread implementation of 3DE in routine clinical practice is limited because the existing software packages are relatively time-consuming and skill demanding. The aim of this study was to test the accuracy and reproducibility of new machine learning- (ML-) based, fully automated software for three-dimensional quantification of RV size and function.Methods: Fifty-six unselected patients with a wide range of RV size and function and image quality, referred for clinically indicated cardiac magnetic resonance (CMR) imaging, underwent a transthoracic 3DE exam on the same day. End-systolic and end-diastolic RV volumes (ESV, EDV) and ejection fraction (EF) were measured using the ML-based algorithm and compared with CMR reference values using Bland-Altman and linear regression analyses.Results: RV function quantification by echocardiography was feasible in all patients. The automatic approach was accurate in 32% patients with analysis time of 15 +/- 1 seconds and 100% reproducible. Endocardial contour editing was necessary after the automated postprocessing in the remaining 68% patients, prolonging analysis time to 114 +/- 71 seconds. With these minimal adjustments, RV volumes and EF measurements were accurate in comparison with CMR reference (biases: EDV, -25.6 +/- 21.1 mL; ESV, -7.4 +/- 16 mL; EF, -3.3% +/- 5.2%) and showed excellent reproducibility reflected by coefficients of variation = 0.95 for all measurements.Conclusions: The new ML-based 3DE algorithm provided accurate and completely reproducible RV volume and EF measurements in one-third of unselected patients without any boundary editing. In the remaining patients, quick minimal editing resulted in reasonably accurate measurements with excellent reproducibility. This approach provides a promising solution for fast three-dimensional quantification of RV size and function.