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

Cell-competition algorithm: a new segmentation algorithm for multiple objects with irregular boundaries in ultrasound

Chung-Ming Chen1, Yi-Hong Chou, Curtis S K Chen

  • 1Institute of Biomedical Engineering, College of Medicine, National Taiwan University, Taipei, Taiwan. chung@ntu.edu.tw

Ultrasound in Medicine & Biology
|December 14, 2005
PubMed
Summary
This summary is machine-generated.

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

Subclinical immunometabolic perturbations in the neonatal lung following maternal microplastic exposure in mice.

Toxicology·2026
Same author

White matter reflects the childhood exposome.

bioRxiv : the preprint server for biology·2026
Same author

Mapping the spatiotemporal continuum of structural connectivity development across the human connectome in youth.

Nature communications·2026
Same author

Reproducibility of Diffusion, Shape, and Connectivity Metrics Across Scanners: Implications for Multi-Site Tractography.

bioRxiv : the preprint server for biology·2026
Same author

A multi-task masked autoencoder with GAN-based augmentation for PD-L1 prediction from chest CT images.

Scientific reports·2026
Same author

Hippo signaling pathway regulates branching morphogenesis of the fetal lung under hypoxia.

Pediatric research·2026

A novel cell-competition algorithm offers accurate simultaneous segmentation of multiple objects in ultrasound images. This method, utilizing cell-based deformation and competition, shows superior performance and robustness in breast sonogram analysis.

Area of Science:

  • Medical Imaging
  • Image Analysis
  • Computational Biology

Background:

  • Accurate segmentation of multiple objects with irregular contours is crucial in ultrasound image analysis.
  • Existing methods may struggle with sporadic spots and complex shapes common in sonograms.

Purpose of the Study:

  • To introduce a new region-based algorithm, the cell-competition algorithm, for simultaneous segmentation of multiple objects in ultrasound images (sonograms).
  • To evaluate the algorithm's accuracy, robustness, and performance compared to existing methods.

Main Methods:

  • The cell-competition algorithm employs simultaneous cell-based region deformation and cell competition.
  • Cells for segmentation are generated using two-pass watershed transformations.
  • Validation was performed on synthetic images with varying contrast-to-noise ratios and real breast sonograms.

Related Experiment Videos

Main Results:

  • The algorithm demonstrated boundaries comparable to manual delineations in both synthetic and real ultrasound images.
  • It proved robust to variations in regions-of-interest and watershed transformation thresholds.
  • The cell-competition algorithm outperformed the region-competition algorithm in segmenting both image types.

Conclusions:

  • The proposed cell-competition algorithm provides a reliable and effective approach for simultaneous multi-object segmentation in ultrasound imaging.
  • Its robustness and superior performance make it a valuable tool for sonogram analysis, particularly for irregular shapes and complex backgrounds.