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

An estimation/correction algorithm for detecting bone edges in CT images.

W Yao1, P Abolmaesumi, M Greenspan

  • 1School of Computing, Queen's University, Kingston, ON, Canada. wyao4@uwo.ca

IEEE Transactions on Medical Imaging
|August 12, 2005
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

Monolithically integrated compact 281 µm long arbitrary polarization to TE transformer.

Optics express·2026
Same author

[Analysis of early complications and risk factors in patients with amyotrophic lateral sclerosis after percutaneous endoscopic gastrostomy].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·2026
Same author

Dupilumab Rapidly Reduces IgE and Eosinophil Values in Kimura Disease: Sustained Remission Achieved.

Journal of investigational allergology & clinical immunology·2025
Same author

[Progress in the application of JAK inhibitors in atopic dermatitis].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2025
Same author

"It's Time to see What I Can Do": A Mixed-Methods Investigation into Trajectories of Resilience in Adolescents during the COVID-19 Pandemic.

Journal of child & adolescent trauma·2024
Same author

Saturation of the compression of two interacting magnetized plasma toroids evidenced in the laboratory.

Nature communications·2024
Same journal

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026
Same journal

Volumetric Functional Ultrasound Imaging in Macaques.

IEEE transactions on medical imaging·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
See all related articles

This study introduces a multiscale method for accurately estimating bone edge direction in computed tomography (CT) scans. This approach enhances bone segmentation by reducing contour errors and improving accuracy in medical imaging.

Area of Science:

  • Medical Imaging and Image Analysis
  • Computational Anatomy
  • Biomedical Engineering

Background:

  • Bone contour direction in computed tomography (CT) images offers crucial anatomical data for segmentation algorithms.
  • Estimating normal direction using a single scale is unreliable due to varying bone sizes and noisy, non-uniform bone pixel intensities in CT images.

Purpose of the Study:

  • To propose and evaluate a multiscale approach for estimating the normal direction of bone edges in CT images.
  • To improve the accuracy and reliability of bone segmentation by addressing challenges of scale and noise.

Main Methods:

  • A multiscale approach is developed to estimate the normal direction of bone edges.
  • Reliability of estimation is calculated and re-scaled to correct the normal direction.

Related Experiment Videos

  • Optimal scale is determined per point for use in an edge detector.

    • Main Results:

    • The multiscale method improves segmentation quality by reducing unexpected edges and contour discontinuities (gaps).
    • The corrected normal direction aids in postprocessing to eliminate false edges.
    • The automatic segmentation algorithm demonstrates effective performance on human pelvis, leg, and wrist CT images.

    Conclusions:

    • The proposed multiscale approach reliably estimates bone edge normal directions in CT images.
    • This method significantly enhances the accuracy of automatic bone segmentation algorithms.
    • The technique offers a robust solution for improving anatomical structure delineation in medical imaging.