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

A method based on multispectral imaging technique for white blood cell segmentation.

Ningning Guo1, Libo Zeng, Qiongshui Wu

  • 1Electronic Information School, Wuhan University, Wuhan, PR China. gzm560726@yahoo.com.cn

Computers in Biology and Medicine
|December 6, 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

Serum 25-hydroxyvitamin D is associated with islet function in postmenopausal women with type 2 diabetes and osteoporosis.

Frontiers in endocrinology·2026
Same author

Associations Between Rumination and the Incidence of First-Episode Major Depressive Disorder in a Sample of Chinese University Students: From a 1-Year Longitudinal Study.

Depression and anxiety·2026
Same author

Mitochondrial translational control in cardiovascular diseases: from mechanisms to therapies.

Redox biology·2026
Same author

A current view on molecular mechanisms and machineries driving unconventional pathways of protein secretion.

Current opinion in cell biology·2026
Same author

ARMH4 accelerates aging by maintaining a positive-feedback growth signaling circuit.

Nature communications·2025
Same author

A hyperactive splice variant of STAT3 promotes colonic inflammation-associated tumorigenesis in mice.

Science translational medicine·2025

This study introduces a robust multispectral imaging method for analyzing White Blood Cells (WBCs) in bone marrow. The technique uses Support Vector Machines (SVM) for accurate cell segmentation, proving effective across various staining and lighting conditions.

Area of Science:

  • Medical Imaging
  • Hematology
  • Computational Biology

Background:

  • Accurate analysis of White Blood Cells (WBCs) in bone marrow is crucial for diagnosing various hematological conditions.
  • Conventional color imaging methods struggle with device-dependency, affecting image analysis reproducibility.
  • Standard image segmentation techniques often lack robustness against variations in staining and illumination.

Purpose of the Study:

  • To develop a device-independent imaging technique for bone marrow microscopic analysis.
  • To improve the accuracy and robustness of White Blood Cell (WBC) segmentation in microscopic images.
  • To overcome limitations of conventional color imaging in hematological analysis.

Main Methods:

  • Proposed a multispectral imaging technique incorporating spectral calibration for device-independent image acquisition.

Related Experiment Videos

  • Applied Support Vector Machine (SVM) classifier directly to the spectral data of each pixel for image segmentation.
  • Utilized the sequential minimal optimization (SMO) algorithm for feature selection to optimize SVM training time.

    • Main Results:

    • The developed multispectral imaging method yields device-independent images, a significant improvement over conventional methods.
    • Support Vector Machine (SVM) with SMO-based feature selection demonstrated effective and robust segmentation of White Blood Cells (WBCs).
    • Experimental results confirmed the method's insensitivity to variations in smear staining and illumination conditions.

    Conclusions:

    • Multispectral imaging with spectral calibration offers a robust and effective solution for bone marrow White Blood Cell (WBC) image analysis.
    • The SVM classifier, optimized with SMO, provides accurate and reliable cell segmentation.
    • This approach enhances diagnostic capabilities by providing consistent and reproducible microscopic image analysis.