Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Structure and Function of Leukocytes

Structure and Function of Leukocytes

An adult in good health typically has between 4,500 and 11,000 leukocytes, or white blood cells, per microliter of blood, which constitutes about 1% of the total blood volume. Unlike red blood cells, white blood cells contain a nucleus and other cellular organelles but do not have hemoglobin. Most white blood cells reside in connective tissues, particularly in lymphatic organs such as the lymph nodes, with only a small fraction present in circulating blood.
White blood cells protect the body...

Classification of Leukocytes

Classification of Leukocytes

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...

You might also read

Related Articles

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

Sort by

Same author

A logic-based knowledge-driven bidirectional multi-attention GRU framework for fear level classification in humans.

Scientific reports·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 9, 2025

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

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

Published on: November 19, 2018

Domain knowledge-infused pre-trained deep learning models for efficient white blood cell classification.

P Jeneessha¹, Vinoth Kumar Balasubramanian²

¹Department of Information Technology, PSG College of Technology, Coimbatore, 641004, India. jen.it@psgtech.ac.in.

Scientific Reports

|May 4, 2025

Summary

Integrating domain knowledge with image data significantly boosts white blood cell (WBC) classification accuracy in deep learning models. This approach enhances computer-aided diagnosis (CAD) systems, improving medical analysis efficiency and reliability.

Keywords:

Classification Domain knowledge Feature vectors Pre-trained models White blood cells

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Published on: June 19, 2019

Related Experiment Videos

Last Updated: May 9, 2025

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

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

Published on: November 19, 2018

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Preparation of Whole Bone Marrow for Mass Cytometry Analysis of Neutrophil-lineage Cells

Published on: June 19, 2019

Area of Science:

Medical Imaging
Computer Vision
Machine Learning

Background:

Accurate white blood cell (WBC) classification is vital for patient health assessment and treatment validation.
Existing computer-aided diagnosis (CAD) systems face challenges with data insufficiency in medical datasets, limiting deep learning model performance.
Data augmentation and normalization improve data quantity but not quality, highlighting the need for enhanced data utilization.

Purpose of the Study:

To improve the classification performance of pre-trained deep learning models by integrating domain knowledge with image data.
To evaluate the effectiveness of domain knowledge infusion on models like Inception V3, DenseNet 121, ResNet 50, MobileNet V2, and VGG 16.
To analyze the performance improvements on the BCCD and LISC datasets.

Main Methods:

Utilized domain knowledge and image data fusion to enhance pre-trained deep learning models.
Applied the enhanced models to classify WBCs on the BCCD and LISC datasets.
Compared the performance of models with and without infused domain knowledge.

Main Results:

On the BCCD dataset, average accuracies increased across all tested models (Inception V3, DenseNet 121, ResNet 50, MobileNet V2, VGG 16) after incorporating domain knowledge.
Significant accuracy improvements were observed on the LISC dataset as well, with models showing enhanced performance post-domain knowledge infusion.
The study demonstrated substantial gains in WBC classification accuracy by combining domain expertise with deep learning on medical image datasets.

Conclusions:

Integrating domain knowledge with image data is a highly effective strategy for improving deep learning-based WBC classification.
This approach offers a viable solution to the data insufficiency problem in medical datasets, enhancing CAD system accuracy.
The findings support the use of domain knowledge-infused deep learning models for more efficient and reliable medical image analysis.