EchoGNN：使用图神经网络进行可解释的射血分数估计
EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networks
AI总结：
本文提出EchoGNN，利用图神经网络从超声心动图视频中估计射血分数，并通过图权重识别关键帧以提供可解释性，在EchoNet-Dynamic上达到与最先进方法相当的性能。
摘要：
射血分数（EF）是心功能的一项关键指标，可用于识别易发生心力衰竭等心脏功能障碍的患者。EF通过被称为超声心动图（echo）的心脏超声视频进行估计，方法是在特定帧上手动描绘左心室并估计其容积。由于手动过程以及视频质量的差异，这些估计表现出很高的观察者间差异。这些不准确来源以及快速评估的需求，使得可靠且可解释的机器学习技术成为必要。在本研究中，我们提出了EchoGNN，这是一种基于图神经网络（GNN）的模型，用于从超声心动图视频中估计EF。我们的模型首先从一个或多个超声心动图电影序列的帧中推断出一个潜在的超声心动图。随后，它估计该图中节点和边上的权重，以指示有助于EF估计的各个帧的重要性。GNN回归器使用该加权图来预测EF。我们从定性和定量两方面表明，学习到的图权重通过识别EF估计的关键帧提供了可解释性，这些关键帧可用于确定何时需要人工干预。在EchoNet-Dynamic公开EF数据集上，EchoGNN取得了与最先进水平相当的EF预测性能，并提供了可解释性；鉴于该任务固有的高观察者间差异，这一点至关重要。
英文摘要：
Ejection fraction (EF) is a key indicator of cardiac function, allowing identification of patients prone to heart dysfunctions such as heart failure. EF is estimated from cardiac ultrasound videos known as echocardiograms (echo) by manually tracing the left ventricle and estimating its volume on certain frames. These estimations exhibit high inter-observer variability due to the manual process and varying video quality. Such sources of inaccuracy and the need for rapid assessment necessitate reliable and explainable machine learning techniques. In this work, we introduce EchoGNN, a model based on graph neural networks (GNNs) to estimate EF from echo videos. Our model first infers a latent echo-graph from the frames of one or multiple echo cine series. It then estimates weights over nodes and edges of this graph, indicating the importance of individual frames that aid EF estimation. A GNN regressor uses this weighted graph to predict EF. We show, qualitatively and quantitatively, that the learned graph weights provide explainability through identification of critical frames for EF estimation, which can be used to determine when human intervention is required. On EchoNet-Dynamic public EF dataset, EchoGNN achieves EF prediction performance that is on par with state of the art and provides explainability, which is crucial given the high inter-observer variability inherent in this task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
