Related Experiment Video
Updated: Jul 29, 2025
3D Whole-heart Myocardial Tissue Analysis
Published on: April 12, 2017
Segmentation of Anatomical Structures of the Left Heart from Echocardiographic Images Using Deep Learning
Mhd Jafar Mortada1, Selene Tomassini1, Haidar Anbar1
1Department of Information Engineering, Università Politecnica delle Marche, 60121 Ancona, Italy.
Insights
A new deep learning tool accurately segments left heart structures like the left atrium (LA) and left ventricle (LV) endocardium and epicardium in echocardiograms. This automated segmentation supports clinical practice by providing reliable cardiac imaging analysis.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Accurate segmentation of left heart anatomical structures (left atrium, left ventricle endocardium, and epicardium) is crucial for cardiac function evaluation.
- Manual segmentation of echocardiograms is time-consuming and subject to user variability.
Purpose of the Study:
- To develop and validate a deep learning (DL) tool for automated segmentation of left heart structures in echocardiographic images.
- To improve the efficiency and reliability of cardiac structure segmentation for clinical support.
Main Methods:
- A novel DL tool combining YOLOv7 and U-Net architectures was developed.
- The tool was trained and validated on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) dataset, comprising 450 patients' echocardiograms.
- Segmentation focused on left ventricle endocardium (LVendo), left ventricle epicardium (LVepi), and left atrium (LA).
Main Results:
- The DL tool achieved high segmentation accuracy with Dice similarity coefficients of 92.63% for LVendo, 85.59% for LVepi, and 87.57% for LA.
- The system demonstrated reliable performance across different cardiac views and phases (end-systole and end-diastole).
Conclusions:
- The presented DL-based tool offers a reliable and automated solution for segmenting key left heart anatomical structures from echocardiography.
- This technology has the potential to significantly support cardiological clinical practice by streamlining image analysis.
Abstract:
Knowledge about the anatomical structures of the left heart, specifically the atrium (LA) and ventricle (i.e., endocardium-Vendo-and epicardium-LVepi) is essential for the evaluation of cardiac functionality. Manual segmentation of cardiac structures from echocardiography is the baseline reference, but results are user-dependent and time-consuming. With the aim of supporting clinical practice, this paper presents a new deep-learning (DL)-based tool for segmenting anatomical structures of the left heart from echocardiographic images. Specifically, it was designed as a combination of two convolutional neural networks, the YOLOv7 algorithm and a U-Net, and it aims to automatically segment an echocardiographic image into LVendo, LVepi and LA. The DL-based tool was trained and tested on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) dataset of the University Hospital of St. Etienne, which consists of echocardiographic images from 450 patients. For each patient, apical two- and four-chamber views at end-systole and end-diastole were acquired and annotated by clinicians. Globally, our DL-based tool was able to segment LVendo, LVepi and LA, providing Dice similarity coefficients equal to 92.63%, 85.59%, and 87.57%, respectively. In conclusion, the presented DL-based tool proved to be reliable in automatically segmenting the anatomical structures of the left heart and supporting the cardiological clinical practice.
