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 Experiment Videos

[Self-organization neural network based ultrasonic heart image segmentation].

T Wang1, C Zheng, D Li

  • 1High Technology Research Institute, Sichuan Union University, Chengdu 610065.

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi = Journal of Biomedical Engineering = Shengwu Yixue Gongchengxue Zazhi
|January 30, 2003
PubMed
Summary

This study introduces an unsupervised self-organizing neural network for ultrasonic heart image segmentation. The method automatically segments images, outperforming the traditional K-means algorithm.

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

Discrete element analysis of the effect of particle cohesion on die filling behaviour of pharmaceutical powders in a rotary tablet press.

International journal of pharmaceutics·2026
Same author

Dietary hydrolysed tannins regulate carcass performance and meat traits in Hu sheep through microbial regulation.

Animal : an international journal of animal bioscience·2026
Same author

Mechanical power guided lung protective ventilation in acute respiratory failure using the VentCoach approach.

Scientific reports·2026
Same author

Directed pterygomaxillary disjunction versus direct downfracture in Le Fort I osteotomy: application of a fracture quality framework using bilateral ten-point cone-beam computed tomography in a retrospective cohort of 205 patients.

Medicina oral, patologia oral y cirugia bucal·2025
Same author

Search for Millicharged Particles in Proton-Proton Collisions at sqrt[s]=13.6  TeV.

Physical review letters·2025
Same author

Nutritional impacts of dietary selenium and iodine and their interaction on growth performance, antioxidant capacity and bone quality in Longyan ducklings.

British poultry science·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Image segmentation is crucial for multidimensional ultrasonic heart image reconstruction.
  • Accurate segmentation remains a significant challenge in this field.

Purpose of the Study:

  • To develop and evaluate an unsupervised method for ultrasonic heart image segmentation.
  • To compare the proposed method against traditional algorithms like K-means.

Main Methods:

  • Utilized a self-organizing neural network for image segmentation.
  • Employed an unsupervised clustering approach for automatic segmentation.

Main Results:

  • The self-organizing neural network method demonstrated effective automatic segmentation.

Related Experiment Videos

  • Significant benefits were observed compared to the K-means algorithm.

    • Conclusions:

    • The proposed self-organizing neural network offers an effective solution for ultrasonic heart image segmentation.
    • This unsupervised approach provides advantages over conventional methods.