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: Jul 7, 2026

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

VFMStitch: A Vision-Foundation-Model Empowered Framework for 3D Ultrasound Stitching via Geometric-Semantic Feature

Xing Yao1, Nick DiSanto1, Runxuan Yu1

  • 1Vanderbilt University.

Proceedings of Machine Learning Research
|July 6, 2026
PubMed
Summary

Related Concept Videos

Ultrasound II: Endoscopic Ultrasound and FibroScan01:25

Ultrasound II: Endoscopic Ultrasound and FibroScan

Endoscopic Ultrasound (EUS) and FibroScan are valuable diagnostic tools in gastroenterology and hepatology, each with specific applications and techniques.
Endoscopic Ultrasound (EUS):

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same authorSame journal

LOTUS: Latent Outpainting Diffusion Model for Three-Dimensional Ultrasound Stitching.

Proceedings of machine learning research·2026
Same author

SEGMENTATION CONFIDENCE FOR ARBITRARY CNNS.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

From Geometry to Intensity: A Coarse-to-Fine Pipeline for Unsupervised 3D Ultrasound Stitching.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video.

Proceedings of machine learning research·2026
Same author

Kidney Endoscopy Video to Preoperative CT Alignment for Depth Estimation.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

AVA: Automated Viewability Analysis for Ureteroscopic Intrarenal Surgery.

Proceedings of SPIE--the International Society for Optical Engineering·2026

VFMStitch enhances 3D ultrasound (3DUS) stitching by fusing geometric and semantic features from Vision Foundation Models (VFMs). This novel approach improves rigid registration accuracy for challenging 3DUS data.

Area of Science:

  • Medical imaging
  • Computer vision
  • Ultrasound technology

Background:

  • 3D ultrasound (3DUS) stitching expands field-of-view (FOV) by registering overlapping 3DUS volumes.
  • This process is challenging due to large motion, sector-shaped FOV, noise, and artifacts.
  • Vision Foundation Models (VFMs) show promise for medical image registration, but their use in 3DUS stitching is underexplored.

Purpose of the Study:

  • Introduce VFMStitch, a novel framework for 3DUS stitching.
  • Leverage VFM-derived features for robust rigid registration in 3DUS.
  • Evaluate the effectiveness of geometric-semantic fusion for challenging 3DUS stitching.

Main Methods:

  • Developed VFMStitch, a training-free framework integrating point-cloud (PCD) geometric features with DINOv3 semantic descriptors.
Keywords:
DINOv3feature fusionpoint cloudstitchingultrasoundvision foundation model

Related Experiment Videos

Last Updated: Jul 7, 2026

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

  • Applied VFM-derived features for rigid alignment of 3DUS volumes.
  • Conducted extensive experiments to assess registration accuracy.

    • Main Results:

    • VFMStitch significantly improves rigid registration accuracy compared to existing methods.
    • Demonstrated the effectiveness of geometric-semantic fusion for 3DUS stitching.
    • Validated the VFM-empowered approach for challenging scenarios with large motions and artifacts.

    Conclusions:

    • VFMStitch represents a breakthrough in 3D ultrasound stitching.
    • Geometric-semantic fusion using VFM features enhances registration robustness.
    • The proposed method offers a promising solution for expanding 3DUS field-of-view.