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 Video

Updated: Jun 10, 2026

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

Unsupervised segmentation of overlapped nuclei using Bayesian classification.

Chanho Jung1, Changick Kim, Seoung Wan Chae

  • 1Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea. peterjung@kaist.ac.kr

IEEE Transactions on Bio-Medical Engineering
|July 27, 2010
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

Low KIF4A expression is associated with gastric cancer progression and aggressive phenotypes.

Scientific reports·2026
Same author

Multi-Omics and Machine Learning Analyses Reveal PIK3CG, PRKCD, and TRIM22 as Potential Markers of Poor Prognosis and Immune Activation in Glioblastoma.

Journal of Korean medical science·2026
Same author

Tumor-Associated Macrophage Infiltration and PD-L1 Expression in Gastric Cancer According to a Modified TCGA-Based Classification.

Journal of gastric cancer·2026
Same author

Quantitative Histology of Nonmetastatic Regional Lymph Nodes as a Novel Prognostic Indicator in Microsatellite Instability-High Colorectal Cancer.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2025
Same author

From muscle to motion: GaIn nanoparticle-TPU core/shell mesh electrodes for intelligent prosthesis.

Materials horizons·2025
Same author

Automated Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Carcinoma Using Deep Learning on Pretreatment Core Needle Biopsy Samples.

Anticancer research·2025

This study introduces an unsupervised Bayesian classification method for separating overlapped cell nuclei in images. The novel approach improves quantitative analysis by accurately segmenting clumped nuclei using distance transforms and expectation-maximization algorithms.

Area of Science:

  • * Computational biology
  • * Image analysis
  • * Machine learning

Background:

  • * Accurate cell extraction is crucial for quantitative biological analysis.
  • * Overlapped nuclei in cell images pose a significant challenge for automated analysis.
  • * Existing methods often struggle with precise segmentation of clumped nuclei.

Purpose of the Study:

  • * To develop an unsupervised Bayesian classification scheme for separating overlapped nuclei.
  • * To enhance the accuracy of cell image segmentation in automated processes.
  • * To improve quantitative analysis by addressing challenges posed by clumped nuclei.

Main Methods:

  • * Application of distance transform to identify nuclei boundaries.
  • * Modeling the topographic surface of nuclei as a mixture of Gaussians.

More Related Videos

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Related Experiment Videos

Last Updated: Jun 10, 2026

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

  • * Employing the expectation-maximization (EM) algorithm for distribution learning.
  • * Incorporating prior knowledge of regular nuclei shapes for improved segmentation.

    • Main Results:

    • * The proposed Bayesian classification scheme effectively separates overlapped nuclei.
    • * Experimental results demonstrate superior segmentation performance compared to conventional methods.
    • * The method accurately identifies and segments clumped nuclei, enhancing quantitative analysis.

    Conclusions:

    • * The unsupervised Bayesian approach offers a robust solution for overlapped nuclei segmentation.
    • * This method significantly improves the accuracy of automated cell extraction processes.
    • * The technique provides a valuable tool for more reliable quantitative analysis of cell images.