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

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.

References in corpus (2)

• A Survey on Deep Learning in Medical Image Analysis
• Anatomically Constrained Neural Networks (ACNN): Application to Cardiac Image Enhancement and Segmentation

Cited by in corpus (28)

• Deep learning for cardiac image segmentation: A review
• Segment Anything Model for Medical Images?
• Cardiac Segmentation with Strong Anatomical Guarantees
• Early Detection of Myocardial Infarction in Low-Quality Echocardiography
• Learning With Context Feedback Loop for Robust Medical Image Segmentation
• Cross-dimensional transfer learning in medical image segmentation with deep learning
• FPUS23: An Ultrasound Fetus Phantom Dataset with Deep Neural Network Evaluations for Fetus Orientations, Fetal Planes, and Anatomical Features
• A Domain Translation Framework with an Adversarial Denoising Diffusion Model to Generate Synthetic Datasets of Echocardiography Images
• Label-free segmentation from cardiac ultrasound using self-supervised learning
• EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
• Investigating Shift-Variance of Convolutional Neural Networks in Ultrasound Image Segmentation
• Bootstrap Representation Learning for Segmentation on Medical Volumes and Sequences
• Active inference and deep generative modeling for cognitive ultrasound
• Supervision by Denoising for Medical Image Segmentation
• Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography
• Synthetic Simplicity: Unveiling Bias in Medical Data Augmentation
• Evaluation of state-of-the-art deep learning models in the segmentation of the heart ventricles in parasternal short-axis echocardiograms
• Bayesian Optimization of 2D Echocardiography Segmentation
• MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image Segmentation
• Echo-DND: A dual noise diffusion model for robust and precise left ventricle segmentation in echocardiography
• UNGT: Ultrasound Nasogastric Tube Dataset for Medical Image Analysis
• Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling
• Generative Adversarial Networks in Ultrasound Imaging: Extending Field of View Beyond Conventional Limits
• Graph Convolutional Neural Networks for Automated Echocardiography View Recognition: A Holistic Approach
• Echocardiography Segmentation with Enforced Temporal Consistency
• Tracking spatial temporal details in ultrasound long video via wavelet analysis and memory bank
• Extraction of volumetric indices from echocardiography: which deep learning solution for clinical use?
• A Multi-Source Ultrasound Benchmark Revealing the Limits of Contemporary Self-Supervised Anomaly Detection Methods