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

Divergence-based framework for diffusion tensor clustering, interpolation, and regularization.

Torsten Rohlfing1, Edith V Sullivan, Adolf Pfefferbaum

  • 1Neuroscience Program, SRI International, Menlo Park, CA, USA. torsten@synapse.sri.com

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

Using deep learning to identify brain networks mediating cognitive and motor impairments in alcohol use disorder.

Translational psychiatry·2026
Same author

Divergent Pathways Taken in Adolescence Predict Embracing or Resisting Moderate-to-Heavy Drinking in Young Adulthood.

Biological psychiatry. Cognitive neuroscience and neuroimaging·2026
Same author

Structural brain recovery following reductions in adolescent and young adult binge drinking: A longitudinal NCANDA study.

Developmental cognitive neuroscience·2025
Same author

Recent drinking in alcohol use disorder as a modifiable risk factor of postural tremor and instability in mild cognitive impairment: An initial study.

Alcohol, clinical & experimental research·2025
Same author

Mutual age-varying influences of binge drinking and cannabis use during emerging adulthood in the NCANDA cohort.

Alcohol, clinical & experimental research·2025
Same author

Socioemotional and Executive Control Mismatch in Adolescence and Risks for Initiating Drinking.

JAMA network open·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 presents a new diffusion tensor combination framework using Kullback-Leibler divergence for averaging, clustering, interpolation, and regularization. This method offers a closed-form solution for combining diffusion tensor imaging data.

Area of Science:

  • Diffusion Tensor Imaging
  • Computational Anatomy
  • Statistical Modeling

Background:

  • Diffusion tensor imaging (DTI) generates complex data requiring robust combination methods.
  • Existing tensor combination techniques may lack a strong theoretical foundation or closed-form solutions.
  • Accurate tensor combination is crucial for applications like atlas generation and noise reduction.

Purpose of the Study:

  • To introduce a novel framework for diffusion tensor combination based on a probabilistic interpretation.
  • To develop a distance measure and weighted average for diffusion tensors using symmetric Kullback-Leibler divergence.
  • To demonstrate the framework's utility in tensor averaging, clustering, interpolation, and regularization.

Main Methods:

  • Interpreting diffusion tensors as covariance matrices of Gaussian probability distributions.

Related Experiment Videos

  • Employing symmetric Kullback-Leibler divergence as a distance metric between diffusion tensors.
  • Deriving a closed-form expression for the distance and weighted average of diffusion tensors.
  • Developing a non-linear two-stage smoothing algorithm for boundary-preserving regularization.

    • Main Results:

    • A closed-form solution for combining diffusion tensors was derived.
    • The framework was successfully applied to generate population atlases from multi-subject DTI data.
    • K-means clustering of tensors resulted in a compact Gaussian mixture model.
    • Tensor interpolation and boundary-preserving regularization of noisy DTI data were demonstrated.

    Conclusions:

    • The proposed framework provides a mathematically sound and versatile method for diffusion tensor combination.
    • This approach facilitates advanced DTI data analysis, including atlas construction and noise reduction.
    • The derived closed-form solutions enhance computational efficiency and accuracy in DTI studies.