人工智能在超声心动图中对左心室射血分数的评估改善：与心脏磁共振成像的对比分析。

Improved assessment of left ventricular ejection fraction using artificial intelligence in echocardiography: A comparative analysis with cardiac magnetic resonance imaging.

机构信息

Department of Internal Medicine and Cardiology, Herzzentrum Dresden, Technische Universität Dresden, Fetscherstr. 76, Dresden 01307, Germany.

出版信息

Int J Cardiol. 2024 Jan 1;394:131383. doi: 10.1016/j.ijcard.2023.131383. Epub 2023 Sep 26.

DOI:10.1016/j.ijcard.2023.131383

PMID:37757986

Abstract

BACKGROUND

Left ventricular ejection fraction (LVEF) measurement in echocardiography (Echo) using the recommended modified biplane Simpson (MBS) method is operator-dependent and exhibits variability. We aimed to assess the accuracy of a novel fully automated (Auto) artificial intelligence (AI) in view selection and biplane LVEF calculation compared to MBS-Echo, with cardiac magnetic resonance imaging (CMR) as reference.

METHODS

Each of the 301 consecutive patients underwent CMR and Echo on the same day. LVEF was measured independently by Auto-Echo, MBS-Echo and CMR. Interobserver (n = 40) and test-retest (n = 14) analysis followed.

RESULTS

A total of 229 patients (76%) underwent complete analysis. Auto-Echo and MBS-Echo showed high correlations with CMR (R = 0.89 and 0.89) and with each other (R = 0.93). Auto underestimated LVEF (bias: 2.2%; limits of agreement [LOA]: -13.5 to 17.9%), while MBS overestimated it (bias: -2.2%; LOA: 18.6 to 14.1%). Despite comparable areas under the curves of Auto- and MBS-Echo (0.93 and 0.92), 46% (n = 70) of MBS-Echo misclassified LVEF by ≥5% units in patients with a reduced CMR-LVEF <51%. Although LVEF bias variability across different LV function ranges was significant (p < 0.001), Auto-Echo was closer to CMR for patients with reduced LVEF, wall motion abnormalities, and poor image quality than MBS-Echo. The interobserver correlation coefficient of Auto-Echo was excellent compared to MBS-Echo (1.00 vs. <0.91) for different readers. True test-retest variability was higher for MBS-Echo than for Auto-Echo (7.9% vs. 2.5%).

CONCLUSION

The tested AI has the potential to improve the clinical utility of Echo by reducing user-related variability, providing more accurate and reliable results than MBS.

摘要

背景

超声心动图（Echo）中使用推荐的改良双平面 Simpson（MBS）法测量左心室射血分数（LVEF）依赖于操作者，并且存在变异性。我们旨在评估一种新型全自动（Auto）人工智能（AI）在视窗选择和双平面 LVEF 计算方面的准确性，与心脏磁共振成像（CMR）作为参考。

方法

301 例连续患者均于同一天行 CMR 和 Echo 检查。由 Auto-Echo、MBS-Echo 和 CMR 独立测量 LVEF。随后进行了观察者间（n=40）和复测（n=14）分析。

结果

共 229 例患者（76%）完成了完整分析。Auto-Echo 和 MBS-Echo 与 CMR 呈高度相关（R=0.89 和 0.89），且彼此之间也呈高度相关（R=0.93）。Auto 低估了 LVEF（偏倚：2.2%；一致性界限 [LOA]：-13.5 至 17.9%），而 MBS 高估了 LVEF（偏倚：-2.2%；LOA：18.6 至 14.1%）。尽管 Auto-Echo 和 MBS-Echo 的曲线下面积相当（0.93 和 0.92），但在 CMR-LVEF<51%的患者中，46%（n=70）的 MBS-Echo 将 LVEF 错误分类≥5%。尽管在不同的左心室功能范围内，LVEF 偏倚的变异性具有显著性（p<0.001），但 Auto-Echo 在 LVEF 降低、壁运动异常和图像质量较差的患者中比 MBS-Echo 更接近 CMR。与 MBS-Echo 相比，Auto-Echo 的观察者间相关系数极好（1.00 与<0.91）。MBS-Echo 的真实复测变异性高于 Auto-Echo（7.9% 与 2.5%）。