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

• Published in: IEEE transactions on medical imaging Vol. 38; no. 9; pp. 2198 - 2210
• Main Authors: Leclerc, Sarah, Smistad, Erik, Pedrosa, Joao, Ostvik, Andreas, Cervenansky, Frederic, Espinosa, Florian, Espeland, Torvald, Berg, Erik Andreas Rye, Jodoin, Pierre-Marc, Grenier, Thomas, Lartizien, Carole, Dhooge, Jan, Lovstakken, Lasse, Bernard, Olivier
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Artificial neural networks; Automation; Cardiacsegmentation and diagnosis; Coders; Correlation coefficient; Correlation coefficients; Databases, Factual; Datasets; Deep Learning; Echocardiography; Echocardiography - methods; Encoders-Decoders; Engineering Sciences; Heart; Heart - diagnostic imaging; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; left atrium; left ventricle; Machine learning; Medical diagnosis; Medical imaging; Myocardium; Neural networks; Signal and Image processing; Three-dimensional displays; Training; Two dimensional analysis; Two dimensional displays; Ultrasonic imaging; Ultrasound; Ventricle; Multimodal cardiac imaging; cardiac strain; deep learning; electromechanical model; left ventricle; synthetic sequences; motion estimation; myocardium; Cardiac segmentation and diagnosis; left atrium; numerical simulation; ultrasound
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2019.2900516

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.