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

Neural network in hematopoietic malignancies.

Gina Zini1, Giuseppe d'Onofrio

  • 1Researcher Center for Clinical Evaluation of Automated Method in Hematology, Hematology Department, Catholic University of Sacred Heart, Policlinico Gemelli, Laboratorio di Ematologia, L.go A. Gemelli 8, 00168, Rome, Italy. recamh@rm.unicatt.it

Clinica Chimica Acta; International Journal of Clinical Chemistry
|July 10, 2003
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

Next Generation Digital Morphology: Blast Preclassification in Bone Marrow Aspirates.

International journal of laboratory hematology·2026
Same author

Performance of Automated Hematology Analyzer Criteria in Detecting Peripheral Blood Smear Abnormalities: A Systematic Literature Review.

International journal of laboratory hematology·2026
Same author

Practical Considerations in the Implementation of Peripheral Smear Review in the Clinical Laboratory.

International journal of laboratory hematology·2026
Same author

Assessment of the Performance of Siemens Scopio Digital Morphology on Bone Marrow Aspirates in Onco-Hematology.

International journal of laboratory hematology·2026
Same author

Preface.

International journal of laboratory hematology·2026
Same author

Developments in the International Journal of Laboratory Hematology.

International journal of laboratory hematology·2026

This study developed an Artificial Neural Network (ANN) to interpret complex hematology data, improving leukemia diagnosis. The ANN effectively clusters normal and abnormal cell signals, paving the way for advanced diagnostic tools.

Area of Science:

  • Hematology
  • Medical Diagnostics
  • Artificial Intelligence in Medicine

Background:

  • Laboratory hematology has seen significant automation, increasing daily full blood counts (FBC) and data volume.
  • Interpreting vast amounts of FBC data and novel parameters requires expert analysis to yield clinical insights.
  • A key challenge is translating numerical data into clinically meaningful information and pre-diagnostic guidelines.

Purpose of the Study:

  • To develop a knowledge-based system using an Artificial Neural Network (ANN) to interpret hematology raw data.
  • To enhance diagnostic capabilities by directly processing ADVIA120 analyzer signals for leukemia classification.
  • To create a system for pre-diagnostic guidelines with high accuracy and quality.

Main Methods:

  • Utilized automated cytochemistry data (Peroxidase activity and Nuclear density) from Bayer H* series and ADVIA120 analyzers.

Related Experiment Videos

  • Developed an ANN software to process 84 ADVIA120 parameter sets, fitting data to normal and pathological archetypes.
  • Collected peripheral blood data from 1000 patients with hematopoietic disorders across 22 Italian centers for ANN training and testing.

    • Main Results:

    • The ANN was successfully trained using labeled samples and constructed pathological archetypes.
    • Preliminary testing demonstrated the ANN's high capability in clustering signals into normal and pathological categories.
    • The system showed encouraging results in differentiating cell types and aiding leukemia classification.

    Conclusions:

    • The developed ANN shows significant potential for improving the diagnostic accuracy of hematological malignancies.
    • The system effectively translates complex raw data into meaningful diagnostic information.
    • Future work will focus on creating applications for discriminating different types of anemia using peripheral blood data.