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

Infiltrating monocytes augment alternative complement activation and exacerbate inherited retinal degeneration in a mouse model.

Research square·2026
Same author

Ethical implications of high attrition in AI-based mental health interventions: a systematic review and meta-analysis.

BMC medical ethics·2026
Same author

Blood-based biomarker discovery in motor neuron disease using nucleic acid-linked immuno-sandwich assay.

Brain communications·2026
Same author

Infiltrating Monocyte Fate Switch in Retinal Degeneration: From Early Pathology to Late Homeostasis.

Research square·2026
Same author

Balloon-occluded hepatic arterial infusion for unresectable hepatocellular carcinoma: a phase II trial interim analysis.

Frontiers in oncology·2026
Same author

Self-Powered Smart Textiles for Accelerated Wound Healing through Band Alignment in Piezoelectric Heterojunctions.

ACS nano·2026
Same journal

LiftReg: Limited Angle 2D/3D Deformable Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Inverse Consistency by Construction for Multistep Deep Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Can Crowdsourced Annotations Improve AI-based Congestion Scoring For Bedside Lung Ultrasound?

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Equivariant Filters for Efficient Tracking in 3D Imaging.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Lobar Lung Density Embeddings with a Transformer encoder (LobTe) to predict emphysema progression in COPD.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

uniGradICON: A Foundation Model for Medical Image Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
See all related articles

Related Experiment Video

Updated: Dec 2, 2025

Highly Resolved Intravital Striped-illumination Microscopy of Germinal Centers
10:07

Highly Resolved Intravital Striped-illumination Microscopy of Germinal Centers

Published on: April 9, 2014

10.4K

Graded Image Generation Using Stratified CycleGAN.

Jianfei Liu1, Joanne Li1, Tao Liu1

  • 1National Eye Institute, National Institutes of Health, Bethesda, MD, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|November 4, 2020
PubMed
Summary
This summary is machine-generated.

Stratified CycleGAN improves medical image quality by grading image quality. This novel approach enhances near-infrared fluorescent retinal images, boosting cell detection accuracy and yielding higher quality synthetic images compared to traditional CycleGAN.

Keywords:
Adaptive opticsCell detectionCycleGANData parsingImage qualityOphthalmologySemi-supervised learning

More Related Videos

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

671
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.2K

Related Experiment Videos

Last Updated: Dec 2, 2025

Highly Resolved Intravital Striped-illumination Microscopy of Germinal Centers
10:07

Highly Resolved Intravital Striped-illumination Microscopy of Germinal Centers

Published on: April 9, 2014

10.4K
Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research
05:22

Author Spotlight: Enhanced Multiplex Immunofluorescent Microscopy Protocol for Neuroscience Research

Published on: June 21, 2024

671
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.2K

Area of Science:

  • Medical imaging
  • Artificial intelligence in healthcare
  • Image processing

Background:

  • CycleGAN is utilized for various medical image generation tasks.
  • Significant variations in image quality pose challenges in advanced medical imaging.
  • Existing CycleGAN methods may not adequately address graded variations in image quality.

Purpose of the Study:

  • To enhance the image quality and content of near-infrared fluorescent (NIRF) retinal images using a novel stratified CycleGAN approach.
  • To address the limitations of traditional CycleGAN in handling medical images with substantial quality variations.
  • To improve the synthesis of medical images exhibiting graded quality differences.

Main Methods:

  • Developed stratified CycleGAN by incorporating image quality grading scores as conditional inputs.
  • Utilized semi-supervised learning to propagate quality grades across the dataset.
  • Integrated an image quality classifier into the CycleGAN discriminator.
  • Validated the method using pairs of NIRF retinal images with and without adaptive optics correction.

Main Results:

  • Stratified CycleGAN generated higher quality synthetic images compared to traditional CycleGAN.
  • Cell detection accuracy on synthetic images showed faithfulness to ground truth.
  • The F1-score for cell detection improved from 76.9 ± 5.7% (traditional CycleGAN) to 85.0 ± 3.4% (stratified CycleGAN).
  • Demonstrated successful restoration of image quality in aberrated images to achieve cellular-level detail.

Conclusions:

  • Stratified CycleGAN effectively improves the synthesis of medical images with graded quality variations.
  • The proposed method offers a significant advancement over traditional CycleGAN for medical imaging applications.
  • Stratified CycleGAN holds potential for generating high-fidelity medical images, aiding in diagnostics and research.