基于深度学习利用二维超声心动图预测右心室射血分数
研究回顾性纳入831例经三维超声心动图测量右心室射血分数的患者,用其3583段二维心尖四腔心切面视频训练时空卷积神经网络,构建集成模型并在365例患者1493段视频的外部数据集验证。集成模型预测右心室射血分数的平均绝对误差在内外部验证集分别为4.57和5.54个百分点,外部验证集中识别右心室功能不全(右心室射血分数<45%)的准确率为78.4%,与专家视觉评估的77.0%相当(P=0.678)。深度学习预测的右心室射血分数与主要不良心脏事件相关,且独立于年龄、性别和左心室收缩功能(HR:0.924 [95%CI:0.862-0.990];P=0.025)。
要点
- 集成模型在外部验证集预测右心室射血分数的平均绝对误差为5.54个百分点。
- 外部验证集识别右心室功能不全(右心室射血分数<45%)准确率78.4%,与专家视觉评估77.0%相当(P=0.678)。
- 深度学习预测的右心室射血分数与主要不良心脏事件独立相关(HR:0.924 [95%CI:0.862-0.990];P=0.025)。
核心结论
- 仅使用二维超声心动图视频,所提出的深度学习工具即可准确评估右心室功能,其诊断和预后能力与三维成像相似。
研究设计与样本
- 回顾性研究,纳入831例经三维超声心动图测量右心室射血分数的患者,获取其3583段二维心尖四腔心切面视频,按80:20比例分为训练集与内部验证集;训练多个时空卷积神经网络预测右心室射血分数,将表现最好的3个网络组合为集成模型,并在包含365例患者1493段视频、中位随访时间1.9年的外部数据集中进一步评估。
诊断标准与关键数值
- 右心室功能不全定义为右心室射血分数<45%。
- 集成模型预测右心室射血分数的平均绝对误差在内部验证集为4.57个百分点,在外部验证集为5.54个百分点。
- 外部验证集中,集成模型识别右心室功能不全的准确率为78.4%,专家视觉评估为77.0%(P=0.678)。
- 深度学习预测的右心室射血分数与主要不良心脏事件相关,独立于年龄、性别和左心室收缩功能(HR:0.924 [95%CI:0.862-0.990];P=0.025)。
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
BACKGROUND: Evidence has shown the independent prognostic value of right ventricular (RV) function, even in patients with left-sided heart disease. The most widely used imaging technique to measure RV function is echocardiography; however, conventional 2-dimensional (2D) echocardiographic assessment is unable to leverage the same clinical information that 3-dimensional (3D) echocardiography-derived right ventricular ejection fraction (RVEF) can provide.
OBJECTIVES: The authors aimed to implement a deep learning (DL)-based tool to estimate RVEF from 2D echocardiographic videos. In addition, they benchmarked the tool's performance against human expert reading and evaluated the prognostic power of the predicted RVEF values.
METHODS: The authors retrospectively identified 831 patients with RVEF measured by 3D echocardiography. All 2D apical 4-chamber view echocardiographic videos of these patients were retrieved (n = 3,583), and each subject was assigned to either the training or the internal validation set (80:20 ratio). Using the videos, several spatiotemporal convolutional neural networks were trained to predict RVEF. The 3 best-performing networks were combined into an ensemble model, which was further evaluated in an external data set containing 1,493 videos of 365 patients with a median follow-up time of 1.9 years.
RESULTS: The ensemble model predicted RVEF with a mean absolute error of 4.57 percentage points in the internal and 5.54 percentage points in the external validation set. In the latter, the model identified RV dysfunction (defined as RVEF <45%) with an accuracy of 78.4%, which was comparable to an expert reader's visual assessment (77.0%; P = 0.678). The DL-predicted RVEF values were associated with major adverse cardiac events independent of age, sex, and left ventricular systolic function (HR: 0.924 [95% CI: 0.862-0.990]; P = 0.025).
CONCLUSIONS: Using 2D echocardiographic videos alone, the proposed DL-based tool can accurately assess RV function, with similar diagnostic and prognostic power as 3D imaging.
引用
- Tokodi, Magyar, Soós, et al. Deep Learning-Based Prediction of Right Ventricular Ejection Fraction Using 2D Echocardiograms. JACC Cardiovasc Imaging. 2023. PMID: 37178072. doi:10.1016/j.jcmg.2023.02.017
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。