Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Transcranial direct current stimulation alleviates depression-like behaviors by activating the ACC-ZI neural circuit.

Brain research bulletin·2026
Same author

Author Correction: The SESAME complex regulates cell senescence through the generation of acetyl-CoA.

Nature metabolism·2026
Same author

Pericentrosomal Redistribution of the Endoplasmic Reticulum Ensures Organelle Symmetric Inheritance and Mitotic Progression.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Association between prognostic nutritional index and mortality in critically ill patients with atrial fibrillation: a retrospective cohort study.

BMC cardiovascular disorders·2026
Same author

Toxicological Evaluation of the Roots of <i>Ficus pandurata</i> Hance var. <i>angustifolia</i> Cheng.

Food science & nutrition·2026
Same author

Huoxue Jiegu compound capsule accelerates tibial fracture healing via angiogenesis-driven repair mechanisms.

Frontiers in medicine·2026

Related Experiment Video

Updated: Sep 8, 2025

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
06:56

Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

Published on: January 7, 2021

2.5K

MobileUNet-FPN: A Semantic Segmentation Model for Fetal Ultrasound Four-Chamber Segmentation in Edge Computing

Bin Pu, Yuhuan Lu, Jianguo Chen

    IEEE Journal of Biomedical and Health Informatics
    |June 14, 2022
    PubMed
    Summary
    This summary is machine-generated.

    A novel AI model, MobileUNet-FPN, accurately segments 13 fetal heart structures from ultrasound images, aiding congenital heart disease diagnosis. This method enhances prenatal screening by overcoming imaging challenges.

    More Related Videos

    Murine Fetal Echocardiography
    08:04

    Murine Fetal Echocardiography

    Published on: February 15, 2013

    17.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    2.9K

    Related Experiment Videos

    Last Updated: Sep 8, 2025

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation
    06:56

    Human Fetal Blood Flow Quantification with Magnetic Resonance Imaging and Motion Compensation

    Published on: January 7, 2021

    2.5K
    Murine Fetal Echocardiography
    08:04

    Murine Fetal Echocardiography

    Published on: February 15, 2013

    17.5K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    2.9K

    Area of Science:

    • Medical imaging
    • Artificial intelligence in healthcare
    • Prenatal diagnostics

    Background:

    • Fetal echocardiography, particularly the apical four-chamber (A4C) view, is crucial for diagnosing congenital heart disease (CHD).
    • Accurate segmentation of fetal heart structures in A4C view is challenging due to ultrasound artifacts, noise, anatomical variability, and boundary discontinuities.
    • Existing methods struggle with the complexity and number of structures requiring segmentation.

    Purpose of the Study:

    • To develop an advanced AI-based method for segmenting multiple key anatomical structures in the fetal A4C view.
    • To address the limitations of current segmentation techniques in fetal cardiac imaging.
    • To establish a new benchmark for the number of segmented structures in fetal echocardiography.

    Main Methods:

    • Proposed a novel deep learning architecture, MobileUNet-FPN, combining MobileNet, UNet, and an explicit Feature Pyramid Network (FPN).
    • Utilized a four-stage MobileNet backbone as the encoder and upsampling operations as the decoder.
    • Implemented a multi-level edge computing system for distributed, parallel training to reduce communication overhead.

    Main Results:

    • The MobileUNet-FPN model demonstrated superior performance in segmenting 13 key heart structures in fetal A4C and femoral-length images.
    • This represents the first AI-based approach capable of segmenting such a large number of anatomical structures in the fetal A4C view.
    • The edge computing system effectively reduced network communication overhead during model training.

    Conclusions:

    • The proposed MobileUNet-FPN model offers a robust and accurate solution for fetal heart structure segmentation in prenatal echocardiography.
    • This AI-driven approach has the potential to significantly improve the early diagnosis of congenital heart disease.
    • The distributed edge computing strategy provides an efficient framework for training complex AI models in multi-institutional settings.