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

Search research articles

Related Experiment Videos

Direct neural network application for automated cell recognition.

Qing Zheng¹, Bruce K Milthorpe, Allan S Jones

¹Graduate School of Biomedical Engineering, University of New South Wales, Sydney, Australia.

Cytometry. Part a : the Journal of the International Society for Analytical Cytology

|December 31, 2003

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

SF3B3-dependent inclusion of STOX1 exon 3 facilitates invasion and tumor progression in colorectal cancer.

Biochimica et biophysica acta. General subjects·2026

Same author

Correction to "In Situ Electron Microscopy Study on Surface Etching/Growth Kinetics of Bi<sub>2</sub>Se<sub>3</sub> Nanosheets".

ACS applied materials & interfaces·2026

Same author

Multi-Omics Analysis Identifies Phosphoglucomutase 2 as a Potential Target to Alleviate Chemoradiotherapy Resistance in Cervical Cancer Cells.

OncoTargets and therapy·2026

Same author

Bax inhibitor-1 confers resistance to Phytophthora parasitica and is antagonized by RTP1 in Arabidopsis.

Stress biology·2026

Same author

Effect of a Novel GLP-1 Analogue Ecnoglutide on the Pharmacokinetics of Rosuvastatin and Digoxin in Healthy Participants.

Diabetes, obesity & metabolism·2026

Same author

Single-cell transcriptomic analysis reveals the T lymphocyte microenvironment and identifies HOPX as a hub gene in membranous nephropathy.

Gene·2026

Same journal

CytoScan: Automated Detection of Technical Anomalies for Cytometry Quality Control.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

Same journal

The 1st Mediterranean Meeting on Flow Cytometry: Forging New Collaborations Across the Mediterranean and Beyond.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

Same journal

Publication Guidelines for Optimized Multiparameter Immunolabeling Panels (OMIPs).

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

Same journal

A Modular High-Parameter Flow Cytometry Framework: Pre-Analytical Optimization and Validation for Clinical Research.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

Same journal

Quantitative Detection of Entotic Cell-In-Cell Structures Using Deformable Segmentation and Deep Learning.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

Same journal

Comparison of Tissue Preparations to Identify and Phenotype T Cells in Human Colorectal Tumor Tissue.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2026

See all related articles

Automated cell recognition in histologic images can be achieved directly using neural networks. This method bypasses traditional segmentation and measurement, achieving high accuracy in classifying cell types from pixel data.

Area of Science:

Histopathology
Computational Biology
Machine Learning

Background:

Automated cell recognition in histologic images is challenging.
Traditional methods involve segmentation, measurement, and classification.
Neural networks have shown promise with morphometric data.

Purpose of the Study:

To assess the feasibility of direct cell classification using neural networks with pixel intensity data.
To evaluate different neural network architectures for classifying cells in complex backgrounds.

Main Methods:

Inputting cell image data directly into neural networks.
Assessing various neural network types for accuracy in cell classification.
Utilizing pixel intensity information for direct classification.

Related Experiment Videos

Main Results:

Simple three-layer and four-layer neural networks achieved high correct recognition rates (97% and 98%).
Successful classification of inflammatory cells from rabbit paravertebral muscle histologic sections.
Demonstrated effectiveness with complex patterned backgrounds.

Conclusions:

Direct classification of visual image pixel data by neural networks is highly accurate.
This approach shows significant potential for automated cell recognition in histology.