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

Transforming Growth Factor beta-2 (TGFβ2) Drives Trabecular Meshwork Progenitor Cell Differentiation Through SMAD2/3 Signalling.

Stem cells (Dayton, Ohio)·2026
Same author

A Perturb-seq screen guided by species divergence uncovers pathways for collateral artery formation.

bioRxiv : the preprint server for biology·2026
Same author

The Development and External Testing of Deep Learning Model for Automated Classification of Intervertebral Disc Degeneration on CT Images.

Journal of imaging informatics in medicine·2026
Same author

Deep learning-based identification and maturation assessment of the zygomaticomaxillary suture in cone-beam computed tomography images.

Progress in orthodontics·2026
Same author

Pain State Classification of Stiff Knee Joint Using Electromyogram for Robot-Based Post-Fracture Rehabilitation Training.

Sensors (Basel, Switzerland)·2025
Same author

Highly deformable and high-performance optical paper-based perovskite terahertz modulator.

Optics express·2025

Related Experiment Video

Updated: Jun 18, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

573

AI-driven generalized polynomial transformation models for unsupervised fundus image registration.

Xu Chen1, Xiaochen Fan2, Yanda Meng3

  • 1Department of Medicine, University of Cambridge, Cambridge, United Kingdom.

Frontiers in Medicine
|July 31, 2024
PubMed
Summary

We developed a new AI model for unsupervised fundus image registration using Generalized Polynomial Transformations (GPT). This method accurately aligns medical images, improving diagnostic capabilities in ophthalmology.

Keywords:
color fundus photographyfoundational modelimage registrationpolynomial transformationunsupervised learning

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K

Related Experiment Videos

Last Updated: Jun 18, 2025

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

573
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.1K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Accurate registration of fundus images is crucial for monitoring eye diseases.
  • Existing methods may struggle with diverse transformations and require extensive training data.

Purpose of the Study:

  • To introduce a novel AI-driven approach for unsupervised fundus image registration.
  • To develop a robust Generalized Polynomial Transformation (GPT) model for simulating various image transformations.

Main Methods:

  • Utilized a Generalized Polynomial Transformation (GPT) model trained on a large synthetic dataset.
  • Implemented a hybrid pre-processing strategy for model-focused input.
  • Evaluated performance on the AREDS dataset using standard image registration metrics.

Main Results:

  • Achieved an average Pearson correlation coefficient (R) of 0.9876 in parameter-level analysis.
  • Demonstrated significant improvements in Structural Similarity Index (SSIM) and Normalized Cross Correlation (NCC) scores.
  • Observed precise matching of optic disc and vessel locations with minimal global distortion.

Conclusions:

  • The GPT model offers a powerful tool for unsupervised fundus image registration.
  • This AI-driven approach shows potential for advancing ophthalmic diagnosis, treatment planning, and disease monitoring.