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: Jan 18, 2026

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

3.3K

Retrieval-Augmented Few-Shot Medical Image Segmentation With Foundation Models.

Lin Zhao, Xiao Chen, Eric Z Chen

    IEEE Transactions on Neural Networks and Learning Systems
    |June 3, 2025
    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

    Leveraging Diffusion Model and Image Foundation Model for Improved Correspondence Matching in Coronary Angiography.

    IEEE transactions on medical imaging·2025
    Same author

    From Compressed-Sensing to Deep Learning MR: Comparative Biventricular Cardiac Function Analysis in a Patient Cohort.

    Journal of magnetic resonance imaging : JMRI·2023
    Same author

    Pyramid Convolutional RNN for MRI Image Reconstruction.

    IEEE transactions on medical imaging·2022
    Same author

    Mitochondrial dysfunction in inflammatory bowel disease alters intestinal epithelial metabolism of hepatic acylcarnitines.

    The Journal of clinical investigation·2020
    Same author

    Skin Lesion Segmentation with C-UNet.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2020
    Same author

    From Deep Learning Towards Finding Skin Lesion Biomarkers.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2020

    This study introduces a new retrieval-augmented method for few-shot medical image segmentation, enhancing accuracy across modalities without retraining. It leverages DINOv2 and SAM 2 for efficient segmentation, aiding clinical decision-making.

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Artificial Intelligence

    Background:

    • Medical image segmentation is vital for clinical decisions but hindered by limited annotated data.
    • Few-shot segmentation (FSS) and foundation models like SAM face challenges in domain generalization and fine-tuning requirements.

    Purpose of the Study:

    • To develop a novel retrieval-augmented framework for few-shot medical image segmentation.
    • To adapt DINOv2 and SAM 2 for improved segmentation performance without domain-specific retraining.

    Main Methods:

    • Utilized DINOv2 features as queries to retrieve similar annotated samples, storing them as memories.
    • Employed SAM 2's memory attention mechanism to condition segmentation generation using retrieved memories.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    737

    Related Experiment Videos

    Last Updated: Jan 18, 2026

    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

    3.3K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    737

    Main Results:

    • Achieved superior performance and generalizability across three diverse medical image segmentation tasks.
    • Demonstrated effective segmentation without the need for retraining or fine-tuning on target domains.

    Conclusions:

    • The proposed method offers a practical and effective solution for few-shot medical image segmentation.
    • This approach shows significant potential as a valuable tool for medical image annotation in clinical settings.