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

The morphological classification of red cells using an image analysing computer.

S A Bentley, S M Lewis

    British Journal of Haematology
    |February 1, 1976
    PubMed
    Summary

    Automated image analysis for red blood cell morphology shows promise. Machine classification error is comparable to human observer inconsistency, suggesting potential for automated blood film examination.

    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

    Practical photonic bandgap structures for high frequency axion haloscopes.

    The Review of scientific instruments·2025
    Same author

    Dark Matter Axion Search with HAYSTAC Phase II.

    Physical review letters·2025
    Same author

    A quantum enhanced search for dark matter axions.

    Nature·2021
    Same author

    A two-year toxicology study of bisphenol A (BPA) in Sprague-Dawley rats: CLARITY-BPA core study results.

    Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2019
    Same author

    Extinction to amphetamine-associated context in female rats is dependent upon conditioned orienting.

    Psychopharmacology·2018
    Same author

    Enteral nutrition in head and neck cancer patients treated with intensity-modulated radiotherapy at a United Kingdom cancer centre.

    Clinical nutrition ESPEN·2017

    Area of Science:

    • Hematology
    • Medical image analysis
    • Computational pathology

    Background:

    • Manual examination of blood films is crucial for diagnosing various conditions.
    • Red blood cell morphology analysis is subjective and prone to inter-observer variability.
    • Automation of red blood cell morphology assessment could improve efficiency and consistency.

    Purpose of the Study:

    • To evaluate the applicability of automated image analysis for red blood cell morphology classification.
    • To compare the consistency of a machine-based classifier with trained human observers.
    • To define a classification scheme for red blood cell morphology.

    Main Methods:

    • Developed a six-category classification scheme for red blood cells (round, elongated, tear drop poikilocytes, helmet cells, irregular cells, spherocytes).

    Related Experiment Videos

  • Acquired measurements (area, perimeter, maximum diameter, integrated optical density) of stained red blood cells using an image analyzing computer.
  • Utilized a multivariate classifier based on derived parameters to categorize red blood cells.

    • Main Results:

    • The machine-based classifier achieved classification accuracy comparable to trained human observers.
    • Inherent error of the automated classifier was similar to the inconsistency observed between human experts.
    • The defined classification scheme and derived parameters showed potential for automated analysis.

    Conclusions:

    • Automated image analysis offers a viable approach for consistent red blood cell morphology assessment.
    • The performance of the machine classifier suggests it can reduce subjectivity in blood film examination.
    • Further development could lead to more efficient and reliable diagnostic tools in hematology.