Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography

TL;DR

This paper evaluates deep learning methods for cardiac structure segmentation in 2D echocardiography using a new large dataset, demonstrating superior performance over traditional methods but highlighting areas for further improvement.

Contribution

Introduction of the CAMUS dataset, the largest annotated dataset for 2D echocardiography, and an assessment of encoder-decoder neural networks for cardiac segmentation.

Findings

Encoder-decoder models outperform traditional methods.

High correlation (0.95) in ventricular volume estimation.

Moderate correlation (0.80) in ejection fraction estimation.

Abstract

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 as well as estimating clinical indices, on a dataset especially designed to answer this objective. We therefore introduce the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) 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.