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

Computer-assisted interpretation of flow cytometry data in hematology

O Thews1, A Thews, C Huber

  • 1Institute of Physiology and Pathophysiology, Johannes Gutenberg-University, Mainz, Germany.

Cytometry
|February 1, 1996
PubMed
Summary

Artificial intelligence aids in diagnosing hematological disorders from flow cytometry data. The system achieves 97% accuracy in classifying acute leukaemias and lymphomas using semantic networks.

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

A multicentre, phase IIa study of zolbetuximab as a single agent in patients with recurrent or refractory advanced adenocarcinoma of the stomach or lower oesophagus: the MONO study.

Annals of oncology : official journal of the European Society for Medical Oncology·2019
Same author

The Danish STR sequence database: duplicate typing of 363 Danes with the ForenSeq™ DNA Signature Prep Kit.

International journal of legal medicine·2018
Same author

Chondrodysplasia with multiple dislocations: comprehensive study of a series of 30 cases.

Clinical genetics·2017
Same author

Influence of the substrate material on the knife-edge based profiling of tightly focused light beams.

Optics express·2016
Same author

Bubble accumulation and its role in the evolution of magma reservoirs in the upper crust.

Nature·2016
Same author

Status of hormones and painkillers in wastewater effluents across several European states-considerations for the EU watch list concerning estradiols and diclofenac.

Environmental science and pollution research international·2016

Area of Science:

  • Hematology
  • Computational Biology
  • Artificial Intelligence

Background:

  • Flow cytometry is crucial for diagnosing hematological malignancies.
  • Accurate subclassification of leukaemias and lymphomas is essential for effective treatment.
  • Current diagnostic methods can be complex and time-consuming.

Purpose of the Study:

  • To develop and validate an AI-powered computer program for diagnosing acute leukaemias and non-Hodgkin lymphomas using flow cytometry data.
  • To leverage semantic networks for representing hematological knowledge and disease patterns.
  • To automate the diagnostic process and improve classification accuracy.

Main Methods:

  • Development of a computer program utilizing artificial intelligence for flow cytometry data analysis.

Related Experiment Videos

  • Formulation of a knowledge base using semantic networks describing normal hematopoiesis and pathological conditions.
  • Implementation of a diagnosis algorithm to compare sample findings with disease-specific antigen expression patterns.
  • Inclusion of double staining data to differentiate mixed cell populations.

    • Main Results:

    • The AI system achieved an overall correct diagnosis rate of 97% across 633 cases.
    • High accuracy was observed in classifying B-cell non-Hodgkin lymphomas (99%).
    • Classification accuracy for B-cell acute lymphoblastic leukaemia was 84%.

    Conclusions:

    • The developed AI program demonstrates high accuracy and potential for computer-assisted diagnosis of hematological malignancies.
    • Semantic networks provide a robust framework for encoding complex hematological knowledge.
    • The system offers a valuable tool for improving the efficiency and precision of flow cytometry data interpretation.