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

You might also read

Related Articles

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

Sort by

Same author

A Label-Free Ultraviolet Photoacoustic Microscopy Enables Nuclear Imaging and Toxicity Assessment in an Intact Brain Organoid.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

SSEL-CPP: A SHAP-based feature-selection ensemble learning framework identifies molecular properties of cell-penetrating peptides.

Protein science : a publication of the Protein Society·2026

Same author

Activatable smart contrast agents for photoacoustic imaging.

Smart molecules : open access·2026

Same author

Multiscale photoacoustic imaging of stroke in preclinical models and future directions toward clinical translation [Invited].

Biomedical optics express·2026

Same author

Pulse Repetition Frequency Tuned Low-Intensity Focused Ultrasound Neuromodulation for Tibial Nerve Targeted Bladder Function Modulation.

IEEE transactions on bio-medical engineering·2026

Same author

Integrative Peptide Drug Development: Chemical Engineering, AI-Driven Design, and Cell-Penetrating Peptides.

Pharmaceutics·2026

Search research articles

Related Experiment Video

Updated: Jan 11, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

Deep learning based label-free virtual staining and classification of human tissues using digital slide scanner.

Santanu Misra¹, Sei Na², Kyoungsook Park³

¹Department of Biophysics, Institute of Quantum Biophysics, Sungkyunkwan University, Suwon 16419, South Korea.

Medical Image Analysis

|November 14, 2025

Summary

This study introduces a high-throughput virtual histology framework using deep learning for rapid, automated processing of unstained tissue slides. The method generates virtual H&E images, achieving 95.9% accuracy in cancer detection, offering a cost-effective alternative to traditional staining.

Keywords:

Bright field Cancer classification Deep learning Digital Slide Scanner High Throughput Virtual staining

More Related Videos

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Published on: May 1, 2019

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

Related Experiment Videos

Last Updated: Jan 11, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Digital Analysis of Immunostaining of ZW10 Interacting Protein in Human Lung Tissues

Published on: May 1, 2019

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

Area of Science:

Digital pathology
Computational histopathology
Artificial intelligence in medicine

Background:

Hematoxylin and eosin (H&E) staining is standard in histopathology but is irreversible, time-consuming, and costly.
Label-free microscopy with deep learning faces challenges in clinical adoption due to speed and system management issues.
Current methods limit subsequent analyses and require extensive chemical handling.

Purpose of the Study:

To develop a high-throughput virtual histology framework for rapid, automated processing of unstained tissue slides.
To generate realistic virtual H&E (VHE) images from unstained bright-field (UBF) images.
To enable accurate cancer detection using both VHE and UBF images.

Main Methods:

Integration of a high-throughput digital multi-slide scanner with deep learning for virtual staining and classification.
Utilizing the NEGCUT model with instance-wise hard negative example generation for unpaired image-to-image translation to create VHE images.
Employing a residual network (ResNet)-based classification model that analyzes both VHE and UBF images.

Main Results:

The framework successfully processed unstained bright-field images from various FFPE tissue samples (lymph nodes, brain, liver).
Generated VHE images faithfully replicated conventional H&E staining, preserving critical morphological features.
Achieved 95.9% accuracy in cancer detection by jointly analyzing VHE and UBF images.
Pathologists confirmed VHE images were diagnostic and indistinguishable from conventional slides in blind evaluations.

Conclusions:

The proposed framework provides a scalable, cost-effective, and efficient alternative to conventional H&E staining.
Enables high-throughput histopathology with reduced time, labor, and chemical usage.
Facilitates advanced analyses on tissue samples previously limited by irreversible staining procedures.