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

Geometrically proper models in statistical training.

Qiong Han1, Derek Merck, Josh Levy

  • 1Medical Image Display & Analysis Group, University of North Carolina, Chapel Hill, North Carolina 27599, USA.

Information Processing in Medical Imaging : Proceedings of the ... Conference
|July 19, 2007
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

Autonomic dysreflexia: the concealed killer behind recurrent cerebral hemorrhage in spinal cord injury-a case report with management insights.

Frontiers in neuroscience·2026
Same author

Roxadustat Ameliorates Thoracic Aortic Dissection by Activating HIF-1α-Mediated Mitophagy to Inhibit Ferroptosis.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026
Same author

Grazing intensity drives above-belowground productivity trade-offs and reveals belowground dominance in temperate herbaceous marsh wetlands.

Frontiers in plant science·2026
Same author

Association between upper limb motor function and balance in patients after stroke: a multicenter cross-sectional study.

Scientific reports·2026
Same author

Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos.

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2026
Same author

Livestock grazing modulated the effects of flooding on ecosystem multifunctionality in the wetland of the lower Tumen River in Northeast China.

Environmental research·2026
Same journal

Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Cycle-Consistent Zero-Shot Through-Plane Super-Resolution for Anisotropic Head MRI.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Brightness-Invariant Tracking Estimation in Tagged MRI.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Using Multiple Instance Learning to Build Multimodal Representations.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds.

Information processing in medical imaging : proceedings of the ... conference·2024
See all related articles

This study introduces a novel method for deformable model segmentation by incorporating explicit legality constraints during training. This ensures proper shape statistics and improves segmentation accuracy for complex objects.

Area of Science:

  • Medical image analysis
  • Computer vision
  • Computational geometry

Background:

  • Deformable model segmentation relies on geometric training for shape and appearance priors.
  • Current methods struggle to enforce shape legality (e.g., preventing self-intersections) during training.
  • Lack of shape legality negatively impacts statistical accuracy and segmentation quality.

Purpose of the Study:

  • To propose a method that incorporates explicit legality constraints into the geometric training process for deformable models.
  • To ensure the generation of statistically valid shapes and improve segmentation outcomes.
  • To enhance the consistency of object parameterization and appearance statistics.

Main Methods:

  • Developed a novel training methodology for deformable models.

Related Experiment Videos

  • Integrated explicit mathematical constraints to enforce shape legality during the geometric training phase.
  • Validated the approach through practical application and analysis of resulting shape probability distributions.

    • Main Results:

    • The proposed method generates shape probability distributions exclusively over proper (legal) objects.
    • Explicit legality constraints lead to more consistent parameterization of object volumes.
    • Demonstrated significant improvements in the accuracy and reliability of segmentation results.

    Conclusions:

    • Incorporating explicit legality constraints into the training process is crucial for robust deformable model segmentation.
    • The method ensures the generation of anatomically plausible shapes, enhancing statistical validity.
    • This approach offers a mathematically sound and practically effective solution for improving segmentation quality.