Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography
Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography
复制标题
DOI：
10.1109/tmi.2019.2900516
复制
发表时间：
2019-09-01
影响因子：
10.6
通讯作者：
Bernard, Olivier
中科院分区：
文献类型：
--
作者：
Leclerc, Sarah;Smistad, Erik;Bernard, Olivier
从2D超声心动图图像描绘心脏结构是建立诊断的常见临床任务。在过去的几十年里，这项任务的自动化一直是深入研究的主题。在本文中，我们评估了最先进的编码器-解码器深度卷积神经网络方法在评估2D超声心动图图像（即在数据集上分割心脏结构和估计临床指标）方面可以走多远，特别是旨在实现这一目标。因此，我们介绍了多结构超声分割数据集的心脏采集，这是用于超声心动图评估的最大的公开可用和完全注释的数据集。该数据集包含来自500名患者的两腔和四腔采集，其中一名心脏病专家对完整数据集进行参考测量，三名心脏病专家对50名患者进行参考测量。结果表明，基于编码器-解码器的架构优于最先进的非深度学习方法，并忠实地再现了舒张末期和收缩末期左心室容积的专家分析，平均相关性为0.95，绝对平均误差为9.5 ml。关于左心室的射血分数，结果与平均相关系数0.80和绝对平均误差5.6%形成更大的对比。虽然这些结果低于观察者间的评分，但仍略差于观察者内的评分。基于这一观察，改进的领域被定义，这为2D超声心动图图像的准确和全自动分析打开了大门。
Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing 2D echocardiographic images, i.e. segmenting cardiac structures and estimating clinical indices, on a dataset, especially, designed to answer this objective. We, therefore, introduce the cardiac acquisitions for multi-structure ultrasound segmentation dataset, the largest publicly-available and fully-annotated dataset for the purpose of echocardiographic assessment. The dataset contains two and four-chamber acquisitions from 500 patients with reference measurements from one cardiologist on the full dataset and from three cardiologists on a fold of 50 patients. Results show that encoder-decoder-based architectures outperform state-of-the-art non-deep learning methods and faithfully reproduce the expert analysis for the end-diastolic and end-systolic left ventricular volumes, with a mean correlation of 0.95 and an absolute mean error of 9.5 ml. Concerning the ejection fraction of the left ventricle, results are more contrasted with a mean correlation coefficient of 0.80 and an absolute mean error of 5.6%. Although these results are below the inter-observer scores, they remain slightly worse than the intra-observer's ones. Based on this observation, areas for improvement are defined, which open the door for accurate and fully-automatic analysis of 2D echocardiographic images.