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

A Novel Radiomics-Integrated Panel for Preoperative Stratification of Pancreatic Neuroendocrine Tumors (PNETs).

Cancers·2026
Same author

Modulation of pulmonary IL-21 expression during latent TB and M. tuberculosis/SIV coinfection.

JCI insight·2026
Same author

Vaginal biomechanical function in premenopausal and postmenopausal women with and without pelvic organ prolapse.

Scientific reports·2025
Same author

Rapid and Precise Topological Comparison with Merge Tree Neural Networks.

IEEE transactions on visualization and computer graphics·2024
Same author

Quantitative and comparative assessment of dyes and protocols for rapid ex vivo microscopy of fresh tissues.

Scientific reports·2024
Same author

Structured illumination microscopy for cancer identification in diagnostic breast biopsies.

PloS one·2024

Related Experiment Video

Updated: Oct 7, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K

Deep learning 2D and 3D optical sectioning microscopy using cross-modality Pix2Pix cGAN image translation.

Huimin Zhuge1, Brian Summa2, Jihun Hamm2

  • 1Department of Biomedical Engineering, Tulane University, 500 Lindy Boggs Center, New Orleans, LA 70118, USA.

Biomedical Optics Express
|January 10, 2022
PubMed
Summary

We developed a Pix2Pix conditional generative adversarial network (cGAN) to convert standard wide-field microscopy images into structured illumination microscopy (SIM) images. This AI approach enables optical sectioning without specialized equipment, improving accessibility for biological imaging.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

730

Related Experiment Videos

Last Updated: Oct 7, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.5K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

730

Area of Science:

  • Biomedical Imaging
  • Computational Microscopy
  • Artificial Intelligence in Science

Background:

  • Structured Illumination Microscopy (SIM) provides optically-sectioned images but requires specialized illumination patterns.
  • Traditional wide-field fluorescence microscopy is cost-effective but lacks optical sectioning capabilities.
  • Bridging the gap between wide-field and SIM imaging can enhance accessibility and reduce costs in microscopy.

Purpose of the Study:

  • To develop a computational method for translating wide-field fluorescence microscopy images into optically-sectioned SIM images.
  • To demonstrate the capability of a Pix2Pix conditional generative adversarial network (cGAN) for cross-modality image translation in microscopy.
  • To explore the potential of the model for reconstructing 3D optically-sectioned volumes from 2D wide-field image stacks.

Main Methods:

  • Implementation of a Pix2Pix conditional generative adversarial network (cGAN) model.
  • Training the cGAN on paired wide-field and SIM microscopy images.
  • Validation of the model's performance on 2D image translation from wide-field to optical sections.
  • Assessment of the model's potential for 3D volume reconstruction from wide-field image stacks.

Main Results:

  • The cGAN model successfully translated 2D wide-field fluorescence microscopy images into optically-sectioned SIM images.
  • The model demonstrated the ability to perform cross-modality image translation, effectively simulating SIM reconstruction.
  • Preliminary results indicate potential for reconstructing 3D optically-sectioned volumes from wide-field image stacks.
  • The model's utility was validated using diverse samples, including fluorescent beads and human tissue.

Conclusions:

  • A Pix2Pix cGAN can effectively convert standard wide-field microscopy images into SIM-like optically-sectioned images.
  • This AI-driven approach offers a cost-effective alternative for achieving optical sectioning without specialized hardware.
  • The developed method shows promise for advancing biological and medical imaging by enhancing the capabilities of conventional microscopy techniques.