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

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
09:56

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

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

Xing Yao1, Runxuan Yu1, Daiwei Lu1

  • 1Vanderbilt University, Nashvile, USA.

Proceedings of Spie--The International Society for Optical Engineering
|July 6, 2026
PubMed
Summary

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

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

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

Proceedings of machine learning research·2026
Same author

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

Proceedings of machine learning research·2026
Same authorSame journal

Kidney Endoscopy Video to Preoperative CT Alignment for Depth Estimation.

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

AVA: Automated Viewability Analysis for Ureteroscopic Intrarenal Surgery.

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

This study introduces an unsupervised method for stitching three-dimensional ultrasound (3DUS) images, improving field-of-view expansion. The new pipeline enhances accuracy and robustness in 3DUS registration for better medical imaging.

Area of Science:

  • Medical Imaging
  • Image Registration
  • Ultrasound Technology

Background:

  • Three-dimensional ultrasound (3DUS) stitching expands the field-of-view (FOV) by registering overlapping 3DUS volumes.
  • Challenges include sector-shaped FOVs, low image quality, noise, artifacts, and large inter-volume motion.
  • Conventional registration methods struggle with 3DUS due to these intrinsic imaging characteristics.

Purpose of the Study:

  • To develop an unsupervised pipeline for accurate and robust 3DUS stitching.
  • To overcome the limitations of conventional registration methods in 3DUS imaging.
  • To improve the field-of-view (FOV) expansion in 3D ultrasound data.

Main Methods:

  • An unsupervised pipeline comprising three stages: geometric feature extraction, point cloud (PCD)-based coarse registration, and intensity-based fine registration.
Keywords:
Point CloudRegistrationStitchingUltrasound

More Related Videos

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue
08:52

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

Related Experiment Videos

Last Updated: Jul 7, 2026

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales
09:56

Automated 3D Optical Coherence Tomography to Elucidate Biofilm Morphogenesis Over Large Spatial Scales

Published on: August 21, 2019

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue
08:52

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

  • Utilized unsupervised geometric feature extraction for improved correspondence identification.
  • Employed a combination of PCD-based coarse and intensity-based fine registration for enhanced accuracy.

    • Main Results:

    • The proposed unsupervised pipeline significantly outperforms existing state-of-the-art 3DUS registration frameworks.
    • Demonstrated superior accuracy and robustness in quantitative and qualitative evaluations.
    • Successfully applied to a 3DUS placenta dataset, showing improved stitching capabilities.

    Conclusions:

    • The developed unsupervised pipeline offers a simple yet effective solution for 3DUS stitching challenges.
    • The method achieves high accuracy and robustness, outperforming current state-of-the-art approaches.
    • This work advances 3DUS image registration for expanded FOV applications, particularly in obstetric imaging.