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

3D OCT-Based Retinal Biomarker Analysis for Automatic Regional-Wise Characterization of Neurodegenerative Diseases.

Journal of imaging informatics in medicine·2026
Same author

Unsupervised Deep Learning-based Keypoint Localization Estimating Descriptor Matching Performance.

IEEE journal of biomedical and health informatics·2026
Same author

DNA methylation biomarkers for cervical cancer risk prediction in HIV-positive Nigerian women.

International journal of cancer·2025
Same author

Pleomorphic Adenoma in the Setting of Triple-Negative Breast Cancer: A Case Report.

Clinical case reports·2025
Same author

Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study.

Heliyon·2024
Same author

Circumpapillary OCT-based multi-sector analysis of retinal layer thickness in patients with glaucoma and high myopia.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2024

Related Experiment Video

Updated: Jun 21, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.5K

ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration.

David Rivas-Villar1,2, Álvaro S Hervella3,4, José Rouco3,4

  • 1Grupo VARPA, Instituto de Investigacion Biomédica de A Coruña (INIBIC), Universidade da Coruña, A Coruña, 15006, A Coruña, Spain. david.rivas.villar@udc.es.

Medical & Biological Engineering & Computing
|July 5, 2024
PubMed
Summary

ConKeD, a new deep learning method, improves retinal image registration by using a novel contrastive learning strategy. This approach effectively learns high-quality descriptors from limited data, outperforming existing techniques.

Keywords:
Feature-based registrationImage registrationMedical imagingRetinal image registrationSelf-supervised learning

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

322
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

Related Experiment Videos

Last Updated: Jun 21, 2025

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
07:11

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

1.5K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

322
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

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Retinal image registration is crucial for medical applications.
  • Current methods often require extensive training data and pre-processing.

Purpose of the Study:

  • To introduce ConKeD, a novel deep learning approach for retinal image registration.
  • To leverage a multi-positive, multi-negative contrastive learning strategy for improved descriptor learning.
  • To reduce reliance on large datasets and complex pre-processing steps.

Main Methods:

  • Developed ConKeD, a deep learning model utilizing a multi-positive, multi-negative contrastive learning strategy.
  • Integrated ConKeD descriptors with domain-specific keypoints (blood vessel bifurcations and crossovers) detected via deep neural networks.
  • Compared ConKeD against triplet loss and single-positive multi-negative alternatives.

Main Results:

  • The multi-positive, multi-negative contrastive learning strategy significantly outperformed triplet loss and single-positive multi-negative methods.
  • ConKeD, combined with domain-specific keypoints, achieved state-of-the-art performance in retinal image registration.
  • The proposed method demonstrated advantages including no pre-processing, reduced training sample requirements, and fewer detected keypoints.

Conclusions:

  • ConKeD offers a promising deep learning-based solution for retinal image registration.
  • The novel contrastive learning strategy enhances descriptor quality, especially with limited data.
  • ConKeD facilitates the development and application of advanced retinal image analysis techniques.