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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Measurement of the Positive Muon Anomalous Magnetic Moment to 127 ppb.

Physical review letters·2025
Same author

Measurement of the Positive Muon Anomalous Magnetic Moment to 0.20 ppm.

Physical review letters·2023
Same author

Wastewater surveillance strategy as an early warning system for detecting cryptic spread of pandemic viruses.

QJM : monthly journal of the Association of Physicians·2023
Same author

Relooking the monkeypox virus during this present outbreak: epidemiology to therapeutics and vaccines.

European review for medical and pharmacological sciences·2022
Same author

COVID-19 vaccines and vaccination program for aging adults.

European review for medical and pharmacological sciences·2021
Same author

Evaluation of molecular interaction, physicochemical parameters and conserved pattern of SARS-CoV-2 Spike RBD and hACE2: in silico and molecular dynamics approach.

European review for medical and pharmacological sciences·2021

Related Experiment Video

Updated: May 15, 2026

Measuring Deformability and Red Cell Heterogeneity in Blood by Ektacytometry
09:12

Measuring Deformability and Red Cell Heterogeneity in Blood by Ektacytometry

Published on: January 12, 2018

Quantitative microscopy approach for shape-based erythrocytes characterization in anaemia.

D K Das1, C Chakraborty, B Mitra

  • 1School of Medical Science and Technology, IIT Kharagpur, India.

Journal of Microscopy
|December 21, 2012
PubMed
Summary

This study introduces a machine learning approach to accurately classify red blood cell abnormalities in anaemia from microscopic images. The method enhances diagnostic accuracy by automating the characterization of various erythrocyte shapes.

More Related Videos

Quantitative Analysis of Viscoelastic Properties of Red Blood Cells Using Optical Tweezers and Defocusing Microscopy
08:03

Quantitative Analysis of Viscoelastic Properties of Red Blood Cells Using Optical Tweezers and Defocusing Microscopy

Published on: March 25, 2022

Identification of a Murine Erythroblast Subpopulation Enriched in Enucleating Events by Multi-spectral Imaging Flow Cytometry
09:40

Identification of a Murine Erythroblast Subpopulation Enriched in Enucleating Events by Multi-spectral Imaging Flow Cytometry

Published on: June 6, 2014

Related Experiment Videos

Last Updated: May 15, 2026

Measuring Deformability and Red Cell Heterogeneity in Blood by Ektacytometry
09:12

Measuring Deformability and Red Cell Heterogeneity in Blood by Ektacytometry

Published on: January 12, 2018

Quantitative Analysis of Viscoelastic Properties of Red Blood Cells Using Optical Tweezers and Defocusing Microscopy
08:03

Quantitative Analysis of Viscoelastic Properties of Red Blood Cells Using Optical Tweezers and Defocusing Microscopy

Published on: March 25, 2022

Identification of a Murine Erythroblast Subpopulation Enriched in Enucleating Events by Multi-spectral Imaging Flow Cytometry
09:40

Identification of a Murine Erythroblast Subpopulation Enriched in Enucleating Events by Multi-spectral Imaging Flow Cytometry

Published on: June 6, 2014

Area of Science:

  • Hematology
  • Medical Imaging
  • Machine Learning

Background:

  • Anaemia is a prevalent global health issue.
  • Current diagnosis relies on subjective microscopic examination of peripheral blood smears, which is prone to errors.
  • Accurate characterization of erythrocyte morphology is crucial for diagnosing and confirming anaemia stages.

Purpose of the Study:

  • To develop and validate a machine learning methodology for automated characterization and classification of erythrocytes in anaemia.
  • To improve the objectivity and accuracy of anaemia diagnosis using microscopic images.
  • To identify optimal features for classifying different types of anaemic erythrocytes.

Main Methods:

  • Peripheral blood smear images were preprocessed using grey world assumption and geometric mean filtering.
  • Erythrocyte segmentation was performed using marker-controlled watershed segmentation.
  • Machine learning classifiers, including logistic regression, were employed for cell characterization based on morphological features.
  • Information gain measure was used to select an optimal subset of features.

Main Results:

  • The proposed machine learning methodology effectively characterized and classified various erythrocyte morphologies associated with anaemia (e.g., tear drop, echinocyte, sickle cells).
  • Feature selection using information gain identified key morphological indicators for classification.
  • Logistic regression achieved superior classification performance compared to other standard classifiers.

Conclusions:

  • Machine learning offers a robust and objective approach to analysing erythrocyte morphology for anaemia diagnosis.
  • Automated analysis of peripheral blood smears can enhance diagnostic accuracy and efficiency.
  • This technique holds potential for improving the management of anaemia worldwide.