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 (CA-MUS) 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 endsystolic 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.Index Terms-Cardiac segmentation and diagnosis, deep learning, ultrasound, left ventricle, myocardium, left atrium.

In this work, we present a novel attention mechanism to refine the segmentation of the endocardium and epicardium in 2D echocardiography. A combination of two U-Nets is used to derive a region of interest in the image before the segmentation. By relying on parameterised sigmoids to perform thresholding operations, the full pipeline is trainable end-to-end. The Refining U-Net (RU-Net) architecture is evaluated on the CAMUS dataset, comprising 2000 annotated images from the apical 2 and 4 chamber views of 500 patients. Although geometrical scores are only marginally improved, the reduction in outlier predictions (from 20% to 16%) supports the interest of such approach.

Clutter in echocardiography hinders the visualization of the heart and reduces the diagnostic value of the images. The detailed mechanisms that generate clutter are, however, not well understood. We present five different hypotheses for generation of clutter based on reverberation artifact with a focus on apical four-chamber view echocardiograms. We demonstrate the plausibility of our hypotheses by in vitro experiments and by comparing the results with in vivo recordings from four volunteers. The results show that clutter in echocardiography can be originated both at structures that lie in the ultrasound beam path and at those that are outside the imaging plane. We show that reverberations from echogenic structures outside the imaging plane can make clutter over the image if the ultrasound beam gets deflected out of its intended path by specular reflection at the ribs. Different clutter types in the in vivo examples show that the appearance of clutter varies, depending on the tissue from which it originates. The results of this work can be applied to improve clutter reduction techniques or to design ultrasound transducers that give higher quality cardiac images. The results can also help cardiologists have a better understanding of clutter in echocardiograms and acquire better images based on the type and the source of the clutter.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.