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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Large-scale multi-sequence pretraining for generalizable MRI analysis in versatile clinical applications.

Nature biomedical engineering·2026
Same author

Author Correction: Large-scale self-supervised video foundation model for intelligent surgery.

NPJ digital medicine·2026
Same author

Epstein-Barr virus-associated lymphoepithelioma-like intrahepatic cholangiocarcinoma with concurrent hepatitis B virus infection: case report and literature review.

Annals of medicine and surgery (2012)·2026
Same author

Structure-Based Design and Optimization of Novel, Potent and Selective Covalent FGFR2/3 Inhibitors with a Tricyclic Core.

Journal of medicinal chemistry·2026
Same author

A universal foundation model for grounded biomedical image interpretation.

Nature communications·2026
Same author

Discovery of a Potent, Selective and In Vivo Active Aurora A PROTAC Degrader from a Promiscuous Kinase Inhibitor.

Journal of medicinal chemistry·2026

Related Experiment Video

Updated: Mar 28, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

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

Published on: April 28, 2022

3.6K

Generative AI for misalignment-resistant virtual staining to accelerate histopathology workflows.

Jiabo Ma1, Wenqiang Li1, Jinbang Li2,3

  • 1Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China.

Nature Communications
|March 27, 2026
PubMed
Summary

This study introduces a virtual staining framework that overcomes data misalignment issues common in digital pathology. The new method achieves high-quality virtual stains even with imperfectly paired data, making it easier to adopt in clinical settings.

More Related Videos

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

1.4K
Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment
11:00

Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment

Published on: March 25, 2020

18.0K

Related Experiment Videos

Last Updated: Mar 28, 2026

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

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

Published on: April 28, 2022

3.6K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

1.4K
Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment
11:00

Visualization, Quantification, and Mapping of Immune Cell Populations in the Tumor Microenvironment

Published on: March 25, 2020

18.0K

Area of Science:

  • Digital Pathology
  • Computational Imaging
  • Histopathology

Background:

  • Traditional histopathology relies on chemical stains, which are time-consuming, resource-intensive, and environmentally burdensome.
  • Virtual staining offers a promising alternative but is limited by the need for perfectly aligned paired data, often unobtainable due to tissue distortion.

Purpose of the Study:

  • To develop a robust virtual staining framework that addresses spatial mismatches in histopathological datasets.
  • To enable high-fidelity virtual staining from imperfectly paired or misaligned data without modifying existing generative models.

Main Methods:

  • A cascaded registration mechanism was employed to mitigate spatial mismatches between images.
  • The framework decouples image generation from spatial alignment, allowing for flexibility with data quality.

Main Results:

  • The proposed framework significantly outperformed state-of-the-art models on five datasets, with a 23.8% improvement in image quality for highly misaligned samples.
  • In blinded trials, pathologists could not reliably distinguish between virtual and chemical stains (52% accuracy).

Conclusions:

  • This virtual staining framework simplifies data acquisition and overcomes key barriers to clinical adoption.
  • The approach offers a scalable solution for integrating advanced virtual staining techniques into routine pathology workflows.