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 Experiment Videos

Virtual immunohistochemistry by conditional generative adversarial networks.

Wei Zhang1, Tik Ho Hui2, May Tse3

  • 1Deparment of Data Science, College of Computing, City Univiersity of Hong Kong, Hong Kong SAR, China.

Scientific Reports
|May 28, 2026
PubMed
Summary

Related Concept Videos

Immunocytochemistry and Immunohistochemistry01:22

Immunocytochemistry and Immunohistochemistry

Immunocytochemistry (ICC) and immunohistochemistry (IHC) are techniques that use antibodies to check for specific proteins or antigens in a sample. The technique was first published by Albert Coons in 1941 to detect the presence of pneumococcal antigen in tissue sections from mice infected with Pneumococcus. Immunocytochemistry helps localization of proteins or antigens in individual cells like blood cells, stem cells, etc., while immunohistochemistry does the same for tissue samples.
These...
Immunofluorescence Microscopy01:12

Immunofluorescence Microscopy

A fluorescence microscope uses fluorescent chromophores called fluorochromes, which can absorb energy from a light source and then emit this energy as visible light. Fluorochromes include naturally fluorescent substances (such as chlorophylls) and fluorescent stains that are added to the specimen to create contrast. Dyes such as Texas red and FITC are examples of fluorochromes. Other examples include the nucleic acid dyes 4’,6’-diamidino-2-phenylindole (DAPI), and acridine orange.
The...

You might also read

Related Articles

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

Sort by
Same author

Evaluation of a Point-of-Care Multiplex PCR Analyser for Detection of <i>Babesia gibsoni</i> in the Canine Population of Hong Kong.

Veterinary sciences·2026
Same author

A Portable and Dual-Button Microneedle Device Enables Intelligent Multimodal Laser Sensing.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Meta-analysis and meta-regression of hearing loss fMRI activity, connectivity, and fluctuation alterations: Heterogeneity of auditory sensory impact across the lifespan.

NeuroImage·2026
Same author

A retrospective study (2019-2024) of neoplastic and non-neoplastic lesions in biopsy samples from exotic pet mammals in Hong Kong.

Journal of comparative pathology·2026
Same author

The hemagglutinin proteins of clades 1 and 2.3.4.4b H5N1 highly pathogenic avian influenza viruses exhibit comparable attachment patterns to avian and mammalian tissues.

bioRxiv : the preprint server for biology·2025
Same author

The hemagglutinin proteins of clades 1 and 2.3.4.4b H5N1 highly pathogenic avian influenza viruses exhibit comparable attachment patterns to avian and mammalian tissues.

Journal of virology·2025
This summary is machine-generated.

This study introduces a Virtual Immunohistochemistry Generative Adversarial Network (VihcGAN) to create virtual IHC images from H&E stains. This AI method accelerates diagnosis by bypassing lengthy staining procedures.

Area of Science:

  • Veterinary Pathology
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Histopathological diagnosis is essential for veterinary patient management.
  • Immunohistochemistry (IHC) provides specific diagnostic information but increases turnaround time.
  • Hematoxylin and eosin (H&E) staining is a foundational diagnostic technique.

Purpose of the Study:

  • To develop a Virtual Immunohistochemistry Generative Adversarial Network (VihcGAN) model.
  • To virtually transform H&E stained canine lymph node images into CD3 and PAX5 IHC stained images.
  • To introduce a novel Stain Intersection over Union (IoU) metric for evaluating virtual IHC accuracy.

Main Methods:

  • Utilized a Generative Adversarial Network (GAN) architecture (VihcGAN) for image transformation.

Related Experiment Videos

  • Developed a new metric, Stain IoU, to assess virtual IHC image quality based on staining characteristics.
  • Applied the VihcGAN model to formalin-fixed canine lymph node sections.

    • Main Results:

    • VihcGAN successfully generated high-resolution (2048x2048) virtual IHC images from H&E stained samples.
    • The VihcGAN model achieved rapid image generation, processing one image per second.
    • Experimental validation, including expert grading, confirmed the effectiveness of VihcGAN and the Stain IoU metric.

    Conclusions:

    • VihcGAN offers a computationally fast and effective method for virtual IHC staining.
    • The approach significantly reduces the time and cost associated with traditional IHC procedures.
    • The VihcGAN model and Stain IoU metric show promise for improving histopathological diagnostic workflows.