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

Segmentation of complex cell clusters in microscopic images: application to bone marrow samples.

Björn Nilsson1, Anders Heyden

  • 1Institute of Laboratory Medicine, Department of Clinical Genetics, Lund University Hospital, Lund, Sweden.

Cytometry. Part a : the Journal of the International Society for Analytical Cytology
|May 26, 2005
PubMed
Summary

A new algorithm can now segment densely packed white blood cells in bone marrow images. This breakthrough enables automated image analysis for bone marrow diagnostics, advancing hematology research.

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

Genome-wide association study in 21,271 individuals identifies 9 novel loci associated with circulating CD34<sup>+</sup> hematopoietic stem and progenitor cell levels.

HemaSphere·2026
Same author

Dual energy CT and deep learning for an automated volumetric segmentation of the major intracranial tissues: Feasibility and initial findings.

Medical physics·2025
Same author

Functional dissection of the gene regulatory mechanism underlying variation in blood CD34<sup>+</sup> cell levels at 1p36.23/ENO1.

Scientific reports·2025
Same author

Putative multiple myeloma susceptibility genes identified by exome sequencing of 347 familial and early-onset cases.

Leukemia·2025
Same author

Longitudinal outcome prediction of prostate cancer patients on active surveillance using multiple instance learning.

Journal of medical imaging (Bellingham, Wash.)·2025
Same author

Genetic variation at PPM1H predicts mobilization efficiency in stem cell donors.

Blood advances·2025

Area of Science:

  • Hematology
  • Computational Biology
  • Medical Imaging

Background:

  • Morphologic examination of bone marrow and peripheral blood is crucial for hematologic diagnosis.
  • Automated leukocyte classification via image analysis is a growing field.
  • Existing segmentation algorithms struggle with complex cell clusters in bone marrow.

Purpose of the Study:

  • To develop a novel algorithm for segmenting densely packed cells in bone marrow images.
  • To address the limitations of current segmentation techniques in complex hematologic samples.

Main Methods:

  • The algorithm oversegments images into cell subparts.
  • It then uses combinatorial optimization to assemble subparts into complete cells.
  • This approach efficiently handles clusters of any cell number.

Related Experiment Videos

Main Results:

  • The algorithm successfully segmented densely clustered leukocytes in bone marrow images.
  • Experimental validation confirmed the algorithm's effectiveness.

Conclusions:

  • This novel algorithm facilitates the first image analysis-based examination of bone marrow samples.
  • It holds potential for other digital cytometry applications requiring cell cluster separation.