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

Classification of Leukocytes01:30

Classification of Leukocytes

2.7K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
2.7K
Flow Cytometry01:23

Flow Cytometry

13.7K
The development of flow cytometry techniques began in 1934 with initial attempts by Andrew Moldavan, a bacteriologist who counted the cells in a flowing capillary system. Moldavan pumped cells through a capillary tube focused under a microscope for visualization. The invention of photometry allowed the measurement of differentially-stained cells, and Louis Kamentsky developed the first multiparameter flow cytometer in 1965 to identify and count the cancer cells in cervical tissue specimens.
In...
13.7K

You might also read

Related Articles

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

Sort by
Same author

Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Prediction.

IEEE journal of biomedical and health informatics·2026
Same author

Research on Optimization of Construction Parameters of Vertical Cross-Layer Fracturing in Thin Interbedded Coalbed Methane Reservoirs.

ACS omega·2026
Same author

Targeting the neurovascular unit in retinal fibrosis: mechanisms and therapeutic perspectives.

Frontiers in medicine·2026
Same author

MVTT-GMamba: A Multimodal Graph Reasoning Framework for Anti-VEGF Efficacy Prediction in Diabetic Macular Edema.

IEEE journal of biomedical and health informatics·2026
Same author

3D TractFormer: 3D Direct Volumetric White Matter Tract Segmentation with Hybrid Channel-Wise Transformer.

Sensors (Basel, Switzerland)·2026
Same author

Enrichment Characteristics and Genetic Analysis of Rare Earth Elements in the Lower Longtan Formation Coal of Qianbei Coalfield, Guizhou Province.

ACS omega·2026

Related Experiment Video

Updated: Sep 13, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.6K

Explainable multimodal hematology analysis for white blood cell classification and attribute prediction.

Getamesay Haile Dagnaw1, Yanming Zhu1, Muhammad Hassan Maqsood1

  • 1School of Information and Communication Technology, Griffith University, Southport, Gold Coast, 4222 QLD, Australia.

Computers in Biology and Medicine
|July 30, 2025
PubMed
Summary

This study introduces a novel multimodal approach using CLIP for white blood cell (WBC) classification and attribute prediction. The method enhances accuracy and interpretability in automated hematological analysis.

Keywords:
Attribute predictionExplainable AIHematology imagesMultimodal embeddingVision–language modelWhite blood cell classification

More Related Videos

Enumeration of Major Peripheral Blood Leukocyte Populations for Multicenter Clinical Trials Using a Whole Blood Phenotyping Assay
14:45

Enumeration of Major Peripheral Blood Leukocyte Populations for Multicenter Clinical Trials Using a Whole Blood Phenotyping Assay

Published on: September 16, 2012

15.1K
Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.7K

Related Experiment Videos

Last Updated: Sep 13, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.6K
Enumeration of Major Peripheral Blood Leukocyte Populations for Multicenter Clinical Trials Using a Whole Blood Phenotyping Assay
14:45

Enumeration of Major Peripheral Blood Leukocyte Populations for Multicenter Clinical Trials Using a Whole Blood Phenotyping Assay

Published on: September 16, 2012

15.1K
Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.7K

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Artificial Intelligence

Background:

  • Automated hematological analysis relies on accurate white blood cell (WBC) classification and morphological attribute prediction.
  • Existing methods may lack detailed interpretability and struggle with class imbalance.

Purpose of the Study:

  • To develop a multimodal visual-language embedding learning approach for enhanced WBC classification and attribute prediction.
  • To improve the interpretability and accuracy of automated hematological analyses.

Main Methods:

  • Utilized the contrastive language image pretraining (CLIP) model for multimodal learning.
  • Created structured natural language prompts for WBC types and morphological attributes.
  • Implemented a joint-task optimization strategy and a multi-task loss function with adaptive weighting.

Main Results:

  • Achieved state-of-the-art performance in both WBC classification and attribute prediction on public datasets.
  • Demonstrated improved interpretability and prediction accuracy through shared semantic space alignment.
  • Effectively addressed class imbalance issues, balancing classification and attribute prediction tasks.

Conclusions:

  • The proposed multimodal visual-language approach significantly advances automated WBC analysis.
  • This method offers a more interpretable and accurate solution for hematological diagnostics.
  • The findings pave the way for more sophisticated AI-driven medical image analysis.