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

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 nomogram as a predictive tool for lymph node metastasis in papillary thyroid carcinoma.

Frontiers in endocrinology·2026

Same author

A Multicellular Coordinated Network Driving Lymphovascular Space Invasion in Endometrioid Endometrial Carcinoma.

Cell proliferation·2026

Same author

Expert consensus on systemic treatment activation and grading evaluation for alopecia areata.

Chinese medical journal·2025

Same author

Lysophosphatidic acid-induced Arf6-driven macropinocytosis of CD147<sup>+</sup> extracellular vesicles promotes sorafenib resistance of hepatocellular carcinoma.

International journal of biological sciences·2025

Same author

Screening of key genes related to disulfidptosis in psoriasis based on the analysis of WGCNA.

Scientific reports·2025

Same author

Nutrient stress diverts RRN3 from rRNA transcription to alternative polyadenylation of autophagy mRNAs in ovarian cancer.

Cell death & disease·2025

Search research articles

Related Experiment Video

Updated: Nov 15, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Deep Learning Feature Extraction Approach for Hematopoietic Cancer Subtype Classification.

Kwang Ho Park¹, Erdenebileg Batbaatar¹, Yongjun Piao²

¹Database and Bioinformatics Laboratory, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, Korea.

International Journal of Environmental Research and Public Health

|March 6, 2021

Summary

This study introduces a novel deep autoencoder approach for classifying hematopoietic cancer subtypes, improving accuracy and addressing data imbalance with synthetic minority oversampling technique (SMOTE). The method effectively identifies key features for precise cancer subtyping.

Keywords:

autoencoder bioinformatics cancer classification data mining hematopoietic cancer machine learning subtype classification

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

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

Published on: April 8, 2015

Related Experiment Videos

Last Updated: Nov 15, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

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

Published on: April 8, 2015

Area of Science:

Oncology
Bioinformatics
Computational Biology

Background:

Hematopoietic cancer presents significant challenges in subtyping due to cellular heterogeneity and limited sample sizes for traditional statistical methods.
Overfitting and data imbalance issues hinder the development of robust classification models for rare cancer subtypes.

Purpose of the Study:

To develop and validate a deep autoencoder-based feature extraction method for accurate hematopoietic cancer subtype classification.
To address data imbalance using the Synthetic Minority Oversampling Technique (SMOTE) and compare performance against traditional methods.

Main Methods:

A deep autoencoder model was employed for feature extraction, incorporating both reconstruction and classification losses.
The Synthetic Minority Oversampling Technique (SMOTE) was applied to handle data imbalance.
Performance was evaluated by comparing the autoencoder approach with traditional feature selection (PCA, NMF) and classification algorithms (LR, RF, KNN, ANN, SVM).
SHAP (Shapley Additive exPlanations) was used for model interpretability to identify important genes/proteins.

Main Results:

The autoencoder-based feature extraction approach demonstrated strong performance in hematopoietic cancer subtype classification.
The optimal model combined SMOTE oversampling with a support vector machine classifier, utilizing an autoencoder with focal and reconstruction losses.
This best model achieved high accuracy (97.01%), recall (92.60%), specificity (99.52%), F1-measure (93.54%), G-mean (97.87%), and balanced accuracy (95.46%).

Conclusions:

Deep autoencoder-based feature extraction offers a promising strategy for accurate hematopoietic cancer subtype classification.
The integration of SMOTE effectively mitigates data imbalance issues, enhancing model robustness.
The proposed methodology provides a powerful tool for understanding and classifying hematopoietic cancers, with potential for clinical application.