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

Objective and subjective data on the real-world usage of pediatric robotic surgery in Germany.

Klinische Padiatrie·2025
Same author

DG-TTA: Out-of-Domain Medical Image Segmentation Through Augmentation, Descriptor-Driven Domain Generalization, and Test-Time Adaptation.

Sensors (Basel, Switzerland)·2025
Same author

Effect of virtual reality on pain and stress in children during Kirschner-wire removal after fracture treatment: a randomized clinical trial.

The British journal of surgery·2025
Same author

Impact of Radiologist Experience on AI Annotation Quality in Chest Radiographs: A Comparative Analysis.

Diagnostics (Basel, Switzerland)·2025
Same author

Are we ready for virtually planned, 3D printed titanium plates for zygoma fractures? - A feasibility study of 16 post-mortem fractures.

Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery·2024
Same author

AcquisitionFocus: Joint Optimization of Acquisition Orientation and Cardiac Volume Reconstruction Using Deep Learning.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 3, 2025

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

23.1K

3d freehand ultrasound reconstruction by reference-based point cloud registration.

Christoph Großbröhmer1, Lasse Hansen2, Jürgen Lichtenstein3

  • 1Institute of Medical Informatics, University of Lübeck, Lübeck, Germany.

International Journal of Computer Assisted Radiology and Surgery
|January 8, 2025
PubMed
Summary

This study improves freehand ultrasound trajectory estimation using a novel point cloud registration pipeline. Our method enhances accuracy by incorporating heatmap predictions and multi-stage refinement, advancing ultrasound reconstruction capabilities.

Keywords:
Point cloudReconstructionRegistrationUltrasound

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

7.9K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K

Related Experiment Videos

Last Updated: Jun 3, 2025

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

23.1K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

7.9K
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Geometric Deep Learning

Background:

  • Estimating trajectories from freehand ultrasound is challenging.
  • Current point cloud registration methods struggle with realistic examination conditions like sparse labels and partial overlap.

Purpose of the Study:

  • To develop an improved pipeline for trajectory estimation from freehand ultrasound data.
  • To enhance point cloud registration by incorporating heatmap predictions and multi-stage refinement.

Main Methods:

  • A three-stage pipeline: Free Point Transformer for pre-registration, HeatReg with support points for refinement, and instance optimization for displacement enhancement.
  • Utilized prior knowledge and gradient keypoints to expand point sets.
  • Evaluated on 42 forearm ultrasound sweeps with optical ground-truth tracking.

Main Results:

  • The proposed pipeline effectively registers freehand intra-patient ultrasound sweeps.
  • The combined approach (Free Point Transformer + HeatReg) improved upon the baseline by 40% (0.96 mm mean directed surface distance).
  • Further refinement enhanced registration accuracy and trajectory estimation.

Conclusions:

  • The developed techniques enable and improve point cloud registration for freehand ultrasound reconstruction.
  • Heatmap incorporation and multi-stage predictions offer significant theoretical and practical advantages.