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 Experiment Video

Updated: May 23, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

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

David Rivas-Villar, Alvaro S Hervella, Jose Rouco

    IEEE Journal of Biomedical and Health Informatics
    |May 21, 2026
    PubMed
    Summary
    This summary is machine-generated.

    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

    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
    Same author

    Fully automatic deep convolutional approaches for the screening of neurodegeneratives diseases using multi-view OCT images.

    Artificial intelligence in medicine·2024

    This study introduces a novel unsupervised method for retinal image registration, eliminating the need for labeled data. The approach achieves performance comparable to supervised methods, advancing medical image analysis.

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Ophthalmology

    Background:

    • Retinal image registration is crucial for clinical applications.
    • Current methods often require scarce labeled medical data.
    • Keypoint and descriptor-based alignment is standard but data-dependent.

    Purpose of the Study:

    • To develop a fully unsupervised retinal image registration pipeline.
    • To eliminate the reliance on labeled data in medical image registration.
    • To create a novel descriptor and detector for unsupervised keypoint localization.

    Main Methods:

    • Developed an unsupervised descriptor learning method for arbitrary locations.
    • Introduced a label-free keypoint detector network estimating descriptor performance.

    Related Experiment Videos

    Last Updated: May 23, 2026

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
    03:31

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

    Published on: December 15, 2023

  • Inverted the conventional approach by conditioning the detector on the descriptor.

    • Main Results:

    • Unsupervised descriptor outperformed state-of-the-art supervised descriptors.
    • Unsupervised detector significantly surpassed existing unsupervised methods.
    • Full registration pipeline achieved performance comparable to supervised methods without labeled data.

    Conclusions:

    • The proposed unsupervised pipeline effectively registers retinal images without labeled data.
    • The label-free approach offers adaptability to other domains and modalities.
    • This method advances unsupervised learning in medical image analysis.