Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Imaging Studies for Cardiovascular System II:Types of Echocardiography

Imaging Studies for Cardiovascular System II:Types of Echocardiography

Echocardiography plays a role in assessing cardiac health and detecting heart conditions, with various types providing critical insights for diagnosis and treatment.
Types of Echocardiography
Transthoracic Echocardiography (TTE)
TTE is the most common type of echocardiogram which involves placing a transducer on the patient's chest, emitting sound waves to create heart images. TTE is invaluable for evaluating the heart's size, structure, and motion, making it particularly useful for...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

LiquidGAN for Handwriting-Based Detection and Severity Classification of Extrapyramidal Symptoms.

Sensors (Basel, Switzerland)·2026

Same author

Vertebra-Level Completeness Analysis in Thoracolumbar Ultrasound Using a YOLO-Based Detection Framework.

Sensors (Basel, Switzerland)·2026

Same author

Voice-Based Assessment of Extrapyramidal Symptoms Using Deep Learning.

Sensors (Basel, Switzerland)·2025

Same author

Next-Gen Medical Imaging: U-Net Evolution and the Rise of Transformers.

Sensors (Basel, Switzerland)·2024

Same author

Advancing Fault Detection in HVAC Systems: Unifying Gramian Angular Field and 2D Deep Convolutional Neural Networks for Enhanced Performance.

Sensors (Basel, Switzerland)·2023

Same author

Modified SqueezeNet Architecture for Parkinson's Disease Detection Based on Keypress Data.

Biomedicines·2022

Search research articles

Related Experiment Video

Updated: May 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

MUF-Net: A Novel Self-Attention Based Dual-Task Learning Approach for Automatic Left Ventricle Segmentation in

Juan Lyu¹, Jinpeng Meng², Yu Zhang¹

¹College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China.

Sensors (Basel, Switzerland)

|May 14, 2025

Summary

This study introduces a new self-attention dual-task learning method for precise left ventricle segmentation in echocardiography. The approach improves cardiac function assessment by enhancing segmentation accuracy and consistency across frames.

Keywords:

left ventricular segmentation optical flow self-attention spatio-temporal feature

More Related Videos

Murine Echocardiography and Ultrasound Imaging

Murine Echocardiography and Ultrasound Imaging

Published on: August 8, 2010

Murine Echocardiography of Left Atrium, Aorta, and Pulmonary Artery

Murine Echocardiography of Left Atrium, Aorta, and Pulmonary Artery

Published on: February 20, 2017

Related Experiment Videos

Last Updated: May 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Murine Echocardiography and Ultrasound Imaging

Murine Echocardiography and Ultrasound Imaging

Published on: August 8, 2010

Murine Echocardiography of Left Atrium, Aorta, and Pulmonary Artery

Murine Echocardiography of Left Atrium, Aorta, and Pulmonary Artery

Published on: February 20, 2017

Area of Science:

Medical Imaging
Artificial Intelligence
Cardiology

Background:

Left ventricular ejection fraction (LVEF) is crucial for cardiac function assessment and heart disease diagnosis.
Echocardiography segmentation is key to determining LVEF, but current methods struggle with low-contrast images and temporal correlations.
Existing algorithms often neglect spatial-temporal information, leading to suboptimal segmentation of the left ventricle.

Purpose of the Study:

To develop an advanced automatic left ventricle segmentation method using deep learning.
To address limitations of current echocardiography segmentation techniques, particularly low contrast and inter-frame inconsistencies.
To improve the accuracy and temporal consistency of left ventricle segmentation for better LVEF estimation.

Main Methods:

A novel self-attention-based dual-task learning framework was proposed.
A multi-scale edge-attention U-Net was used for supervised semantic segmentation of echocardiograms.
An unsupervised optical flow network captured inter-frame changes, integrated via a temporal consistency mechanism for spatio-temporal feature extraction.

Main Results:

The proposed model demonstrated superior performance compared to existing segmentation methods.
Enhanced accuracy in semantic segmentation of the left ventricle was achieved.
Improved segmentation consistency between consecutive echocardiography frames was observed.

Conclusions:

The self-attention dual-task learning approach offers a significant advancement in automatic left ventricle segmentation.
The method effectively overcomes challenges associated with echocardiography image quality and temporal dynamics.
This technique holds promise for more reliable cardiac function assessment through improved LVEF estimation.