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

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

11.9K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
11.9K

You might also read

Related Articles

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

Sort by
Same author

Patient-derived organoids predict personalized drug response and reveal alternative therapeutic options in glioblastoma.

Cell reports. Medicine·2026
Same author

Scattering Coefficient Estimation Using Thin-Film Phantoms with a Spectral-Domain Dental OCT System.

Sensors (Basel, Switzerland)·2026
Same author

Systematic evaluation of mitochondrial morphology regulators for amelioration of neuronal α-synucleinopathy.

NPJ Parkinson's disease·2026
Same author

Adaptive compression framework for giga-pixel whole slide images.

Nature communications·2025
Same author

Operating Room Black Box Technology to Mitigate Local Anesthetic Systemic Toxicity Risk Associated With Liposomal Bupivacaine Administration.

Journal of perianesthesia nursing : official journal of the American Society of PeriAnesthesia Nurses·2025
Same author

S2L-CM: Scribble-supervised nuclei segmentation in histopathology images using contrastive regularization and pixel-level multiple instance learning.

Computers in biology and medicine·2025

Related Experiment Video

Updated: Nov 16, 2025

Simultaneous Label-Free Autofluorescence Multi-Harmonic Microscopy
09:19

Simultaneous Label-Free Autofluorescence Multi-Harmonic Microscopy

Published on: August 29, 2025

369

DeepHCS++: Bright-field to fluorescence microscopy image conversion using multi-task learning with adversarial losses

Gyuhyun Lee1, Jeong-Woo Oh2, Nam-Gu Her3

  • 1Department of Computer Science and Engineering, Ulsan National Institute of Science and Technology (UNIST), South Korea.

Medical Image Analysis
|February 28, 2021
PubMed
Summary

This study introduces a new method to create fluorescence microscopy images from bright-field images, aiding drug screening. The deep learning approach automates fluorescence image generation, reducing preparation time and improving cell analysis.

Keywords:
ApoptosisBright-field microscopyCytoplasmDAPIDeep learningFluorescence microscopyHigh-content screeningPrecision medicine

More Related Videos

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
09:33

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

8.3K
Workflow for High-content, Individual Cell Quantification of Fluorescent Markers from Universal Microscope Data, Supported by Open Source Software
09:57

Workflow for High-content, Individual Cell Quantification of Fluorescent Markers from Universal Microscope Data, Supported by Open Source Software

Published on: December 16, 2014

13.3K

Related Experiment Videos

Last Updated: Nov 16, 2025

Simultaneous Label-Free Autofluorescence Multi-Harmonic Microscopy
09:19

Simultaneous Label-Free Autofluorescence Multi-Harmonic Microscopy

Published on: August 29, 2025

369
Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
09:33

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

8.3K
Workflow for High-content, Individual Cell Quantification of Fluorescent Markers from Universal Microscope Data, Supported by Open Source Software
09:57

Workflow for High-content, Individual Cell Quantification of Fluorescent Markers from Universal Microscope Data, Supported by Open Source Software

Published on: December 16, 2014

13.3K

Area of Science:

  • Biomedical Imaging
  • Computational Biology
  • Cell Biology

Background:

  • High-content drug screening relies on fluorescence microscopy to analyze cellular biomarkers like apoptosis, nuclei, and cytoplasm.
  • Traditional fluorescence imaging requires extensive tissue preparation, limiting throughput and increasing labor.
  • Automating fluorescence image generation from bright-field microscopy can significantly streamline drug discovery processes.

Purpose of the Study:

  • To develop a novel microscopy image translation method for converting bright-field images into multiple fluorescence channels.
  • To enable visualization of cell apoptosis, nuclei, and cytoplasm from a single bright-field image.
  • To enhance the efficiency and throughput of high-content drug screening.

Main Methods:

  • A deep convolutional neural network (CNN) was trained using paired bright-field and fluorescence microscopy images.
  • The model employed multi-task learning with adversarial losses for accurate and realistic image generation.
  • The method was trained on end-to-end image-to-image translation using a dataset of glioblastoma patient samples.

Main Results:

  • The proposed method successfully generated synthetic fluorescence images comparable in accuracy to real fluorescence microscopy images.
  • Quantitative metrics including cell number correlation (CNC), PSNR, SSIM, and R² correlation validated the model's efficacy.
  • The generated images accurately represented cell apoptosis, nuclei, and cytoplasm.

Conclusions:

  • The novel deep learning-based image translation method automates the generation of crucial fluorescence biomarkers from bright-field images.
  • This approach significantly reduces sample preparation time and labor, thereby increasing screening throughput.
  • The method provides a powerful tool for analyzing drug responses in high-content screening applications.