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

Inter and intra-modal deformable registration: continuous deformations meet efficient optimal linear programming.

Ben Glocker1, Nikos Paragios, Nikos Komodakis

  • 1GALEN Group, Laboratoire de Mathématiques Appliquées aux Systèmes, Ecole Centrale de Paris. nikos@ecp.fr

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

Disparate privacy risks from medical AI.

Nature·2026
Same author

Latent Causal Modeling for 3D Brain MRI Counterfactuals.

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)·2026
Same author

Average Calibration Losses for Reliable Uncertainty in Medical Image Segmentation.

IEEE transactions on medical imaging·2026
Same author

Optimization and External Validation of a Deep Learning Model for Segmentation and Quantification of Traumatic Brain Injury Lesions on Head Computed Tomography.

Journal of neurotrauma·2026
Same author

Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results.

Computers in biology and medicine·2025
Same author

TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods: a Korean translation.

Ewha medical journal·2025
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 new non-rigid volume registration method using discrete labeling and linear programming. This approach optimizes image registration by finding a minimal path in a weighted graph, offering a computationally efficient and globally sub-optimal solution.

Area of Science:

  • Medical image analysis
  • Computational geometry
  • Optimization algorithms

Background:

  • Non-rigid volume registration is crucial for medical image analysis, enabling accurate comparisons and fusion of anatomical data.
  • Existing methods often struggle with computational complexity and achieving globally optimal solutions for complex deformations.

Purpose of the Study:

  • To develop a novel non-rigid volume registration framework utilizing discrete labeling and linear programming.
  • To reformulate the registration problem as a minimal path extraction in a weighted graph for efficient computation.

Main Methods:

  • The proposed method represents registration solutions using discrete labels assigned to predefined displacements.
  • A graph topology is constructed based on a regular grid superimposed onto the volume, with links encoding smoothness and deformation costs.

Related Experiment Videos

  • Higher-order polynomials express volume deformation, and efficient linear programming guarantees a globally sub-optimal solution within a defined bound.

    • Main Results:

    • The method is gradient-free and adaptable to various similarity metrics through graph construction.
    • Experimental validation on simulated and manually segmented data demonstrates the approach's effectiveness and potential.
    • The framework provides a computationally tractable solution for non-rigid volume registration.

    Conclusions:

    • The proposed discrete labeling and linear programming approach offers a powerful and efficient solution for non-rigid volume registration.
    • The method's flexibility in encoding similarity metrics and its guaranteed sub-optimal solution make it highly promising for medical imaging applications.