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 Videos

Super-resolution registration using tissue-classified distance fields.

G Elisabeta Marai1, David H Laidlaw, Joseph J Crisco

  • 1Department of Computer Science, Brown University, Providence, RI 02912, USA. gem@cs.brown.edu

IEEE Transactions on Medical Imaging
|February 14, 2006
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

Kinematic tracking of the small bones of the wrist in sequential 3DCT and dynamic 4DCT volume images using open-source Hierarchical 3D Registration, a module within SlicerAutoscoper<sup>M</sup>.

Biomedical engineering online·2026
Same author

Advancing Normal Tissue Complication Probability Modeling with Supervised Contrastive Learning for Predicting Osteoradionecrosis.

Proceedings of the ... Symposium on Applied Computing. Symposium on Applied Computing·2026
Same author

Small bone replacement leads to greater gait asymmetry, cartilage damage, and osteophyte formation than ligament injury in a porcine wrist model.

Osteoarthritis and cartilage open·2026
Same author

Dual-Attention BiLSTM for Interpretable Forecasting of Treatment Toxicities.

... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics·2026
Same author

General microstructure factor analysis of diffusion MRI in gray-matter predicts cognitive scores.

NeuroImage·2026
Same author

Hybrid Computer Vision Model to Predict Lung Cancer in Diverse Populations.

JCO clinical cancer informatics·2026
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
See all related articles

This study introduces a new method for precise bone registration in computed tomography (CT) scans. The technique achieves subvoxel accuracy, significantly improving bone position and orientation analysis in medical imaging.

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Computational Anatomy

Background:

  • Accurate registration of anatomical structures across multiple medical imaging volumes is crucial for quantitative analysis.
  • Existing methods may lack the required precision, especially for small anatomical features or complex motion scenarios.
  • Subvoxel accuracy is often desired for detailed intra-subject, same-modality registration applications.

Purpose of the Study:

  • To develop and validate a novel method for subvoxel accurate registration of bone positions and orientations across multiple computed tomography (CT) volumes.
  • To enable registration of multiple bones, including those with features commensurate with voxel dimensions.
  • To address challenges in registering objects with complex motion or those outside each other's immediate capture region.

Related Experiment Videos

Main Methods:

  • Extraction of a geometric object model from a reference CT volume.
  • Generation of super-resolution distance fields using unsupervised tissue classification for each volume.
  • Utilizing distance fields and the geometric model for object registration.
  • Inferring a motion-directed hierarchy for multi-object registration beyond direct capture regions.

Main Results:

  • The proposed method achieves subvoxel accuracy in bone registration.
  • Demonstrated ability to register multiple bones within a set of CT volumes.
  • Significant accuracy improvements of 74% compared to traditional grey-value registration on human wrist data.
  • Successful registration of objects with inferred motion hierarchies.

Conclusions:

  • The developed method offers a robust and highly accurate solution for intra-subject, same-modality CT image registration.
  • It surpasses conventional grey-value registration techniques in accuracy for bone registration.
  • The technique is valuable for applications requiring precise anatomical landmark localization and tracking across serial CT scans.