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

TCAB1: a potential target for diagnosis and therapy of head and neck carcinomas.

Molecular cancer·2014
Same author

Probability method for Cerenkov luminescence tomography based on conformance error minimization.

Biomedical optics express·2014
Same author

MDRL lncRNA regulates the processing of miR-484 primary transcript by targeting miR-361.

PLoS genetics·2014
Same author

From PET/CT to PET/MRI: advances in instrumentation and clinical applications.

Molecular pharmaceutics·2014
Same author

Growth, Feed Utilization and Blood Metabolic Responses to Different Amylose-amylopectin Ratio Fed Diets in Tilapia (Oreochromis niloticus).

Asian-Australasian journal of animal sciences·2014
Same author

The association of menstrual and reproductive factors with thyroid nodules in Chinese women older than 40 years of age.

Endocrine·2014

Related Experiment Video

Updated: Jun 12, 2025

Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

17.3K

Implementation of resource-efficient fetal echocardiography detection algorithms in edge computing.

Yuchen Zhu1, Yi Gao2, Meng Wang1

  • 1School of Information Engineering, China University of Geosciences, Beijing, China.

Plos One
|September 23, 2024
PubMed
Summary

New AI models for fetal echocardiography (ultrasound of the fetal heart) offer real-time analysis on edge devices. These resource-efficient algorithms significantly reduce model size and improve speed for clinical use.

More Related Videos

Hemodynamic Precision in the Neonatal Intensive Care Unit using Targeted Neonatal Echocardiography
09:31

Hemodynamic Precision in the Neonatal Intensive Care Unit using Targeted Neonatal Echocardiography

Published on: January 27, 2023

869
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

6.1K

Related Experiment Videos

Last Updated: Jun 12, 2025

Murine Fetal Echocardiography
08:04

Murine Fetal Echocardiography

Published on: February 15, 2013

17.3K
Hemodynamic Precision in the Neonatal Intensive Care Unit using Targeted Neonatal Echocardiography
09:31

Hemodynamic Precision in the Neonatal Intensive Care Unit using Targeted Neonatal Echocardiography

Published on: January 27, 2023

869
A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn
11:27

A Modified Sonographic Algorithm for Image Acquisition in Life-Threatening Emergencies in the Critically Ill Newborn

Published on: April 7, 2023

6.1K

Area of Science:

  • Medical Artificial Intelligence
  • Cardiovascular Imaging
  • Embedded Systems

Background:

  • Deep learning shows promise in fetal echocardiography analysis.
  • Limited processing power of edge devices restricts real-time clinical applications of AI in this field.

Purpose of the Study:

  • To develop resource-efficient AI algorithms for real-time fetal echocardiography detection and tracking on edge devices.
  • To enable intelligent echocardiography equipment for enhanced clinical practice.

Main Methods:

  • Developed the YOLOv5s_emn (Extremely Mini Network) Series based on the YOLOv5s architecture.
  • Employed backbone substitution, pruning, and inference optimization techniques.
  • Tested models on NVIDIA Jetson Nano for performance evaluation.

Main Results:

  • YOLOv5s_emn models achieved a 5%-19% reduction in size and parameters compared to YOLOv5s.
  • Demonstrated superior inference speed, with improvements of 52.8-125.0 ms/f over YOLOv5s.
  • Maintained high accuracy while significantly enhancing efficiency.

Conclusions:

  • The YOLOv5s_emn Series offers a viable solution for real-time fetal echocardiography on resource-constrained edge devices.
  • These optimized models have the potential to advance intelligent medical equipment and support clinical decision-making.