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

Label-Free Multimodal Imaging Microscope for Damaged Cell Membrane Detection and Single-Cell Characterization.

ACS sensors·2025
Same author

Refractive Index Morphology Imaging Microscope System Utilizing Polarization Multiplexing for Label-Free Single Living Cells.

ACS sensors·2024
Same author

Dynamic deformation measurement with 2-frame phase-shifting speckle interferometry based on speckle statistics and wavefront multiplexing.

The Review of scientific instruments·2024
Same author

Imaging the intracellular refractive index distribution (IRID) for dynamic label-free living colon cancer cells via circularly depolarization decay model (CDDM).

Biomedical optics express·2024
Same author

Alternating projection combined with fast gradient projection (FGP-AP) method for intensity-only measurement optical diffraction tomography in LED array microscopy.

Biomedical optics express·2024
Same author

LED array microscopy system correction method with comprehensive error parameters optimized by phase smoothing criterion.

Biomedical optics express·2023

Related Experiment Video

Updated: Jun 29, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.5K

The virtual staining method by quantitative phase imaging for label free lymphocytes based on self-supervised

Lu Zhang1, Shengjie Li1, Huijun Wang1

  • 1School of Instrument Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.

The Review of Scientific Instruments
|April 1, 2024
PubMed
Summary

Quantitative phase imaging (QPI) now offers virtual staining for label-free lymphocytes, mimicking clinical standards. This AI-driven approach accurately replicates stained cell features from 3D QPI data, aiding diagnostics.

More Related Videos

A Technique to Simultaneously Visualize Virus-Specific CD8+ T Cells and Virus-Infected Cells In situ
20:47

A Technique to Simultaneously Visualize Virus-Specific CD8+ T Cells and Virus-Infected Cells In situ

Published on: August 13, 2009

12.1K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

Related Experiment Videos

Last Updated: Jun 29, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.5K
A Technique to Simultaneously Visualize Virus-Specific CD8+ T Cells and Virus-Infected Cells In situ
20:47

A Technique to Simultaneously Visualize Virus-Specific CD8+ T Cells and Virus-Infected Cells In situ

Published on: August 13, 2009

12.1K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K

Area of Science:

  • Biomedical optics
  • Computational pathology
  • Artificial intelligence in medicine

Background:

  • Quantitative phase imaging (QPI) provides label-free 3D cell morphology but lacks the visual features of traditional stained pathology slides.
  • Clinical diagnostics rely on 2D color features from stained cells, presenting a gap for QPI adoption.
  • Obtaining paired QPI and stained images of the exact same living cell is challenging.

Purpose of the Study:

  • To develop a virtual staining method for label-free lymphocytes using QPI data.
  • To bridge the gap between QPI's 3D structural information and the 2D color features required for clinical diagnosis.
  • To enable accurate pathological assessment of lymphocytes without traditional staining.

Main Methods:

  • A self-supervised iterative Cycle-Consistent Adversarial Network (CycleGAN) deep learning model was employed.
  • 3D phase information from QPI was used to train the CycleGAN to generate 2D virtual staining images.
  • The iterative approach provided a trained stained result as ground truth for error evaluation, overcoming the lack of paired data.

Main Results:

  • The virtual staining method achieved a structural similarity index of 0.86 for 8756 lymphocytes compared to the clinical gold standard.
  • Area errors in the 2D virtual stained lymphocytes were below 3.59%.
  • Mean errors for nuclear-to-cytoplasmic ratio (2.69%) and color deviation (<6.67%) demonstrated high fidelity to stained cell features.

Conclusions:

  • The proposed CycleGAN-based virtual staining method effectively translates 3D QPI data into clinically relevant 2D stained-like images.
  • This technique allows for label-free pathological analysis of lymphocytes, meeting diagnostic requirements without cell fixation or staining.
  • The high accuracy in structural similarity and feature ratios validates the potential of virtual staining in routine diagnostics.