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

Localized components analysis.

Dan Alcantara1, Owen Carmichael, Eric Delson

  • 1Computer Science, University of California, Davis, 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

Atypical manifestations of dengue in pediatric patients hospitalized during the 2023-2024 epidemic in Argentina: a multicenter registry.

European journal of pediatrics·2026
Same author

Invasive Pneumococcal Disease in Argentine Children After Widespread PCV13 Use: Burden, Potential PCV20 Coverage and Mortality Risk Factors Across Three Years of Surveillance.

The Pediatric infectious disease journal·2026
Same author

Complex interplay of astrogliosis and pathology in preclinical Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Self and informant ratings of depression and everyday functioning in relation to NIH Toolbox Cognition Battery performance.

Aging & mental health·2026
Same author

Coumarin-Thiourea Hybrids: Structural Features Governing CA Inhibition and Antiproliferative Effects.

International journal of molecular sciences·2026
Same author

Strong Antiproliferative Activity Observed in Hammett-Guided Electronic Modulation of GPx-Mimetic Pathways in Aryl Selenoureas.

International journal of molecular sciences·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

We developed Localized Components Analysis (LoCA) to describe shape variations in biomedical objects. LoCA offers a flexible way to represent complex shapes, improving upon existing methods for intuitive analysis.

Area of Science:

  • Biomedical imaging and shape analysis
  • Computational geometry and topology
  • Machine learning for pattern recognition

Background:

  • Analyzing surface shape variation in biomedical objects is crucial for understanding biological processes and disease.
  • Existing methods for shape representation often struggle to balance localization and conciseness of features.
  • A need exists for methods that can capture intuitive modes of shape variation in complex datasets.

Purpose of the Study:

  • Introduce Localized Components Analysis (LoCA) for describing surface shape variation in biomedical object ensembles.
  • Optimize for spatially localized shape components while allowing a flexible trade-off between locality and conciseness.
  • Compare LoCA against existing shape representation methods to demonstrate its superior performance.

Main Methods:

Related Experiment Videos

  • Developed a novel linear subspace method for shape representation.
  • Formulated locality based on pairwise surface point compatibility.
  • Optimized for localized components, enabling a tunable locality-conciseness trade-off.
  • Applied LoCA to 2D and 3D biomedical shape ensembles.

Main Results:

  • LoCA demonstrated superior ability in modulating the locality-conciseness trade-off compared to competing methods.
  • Generated shape components that correspond to intuitive modes of shape variation.
  • The formulation of locality enabled flexible and spatially-localized shape descriptions.
  • Showcased higher-order properties like spatial symmetry in shape descriptions.

Conclusions:

  • Localized Components Analysis (LoCA) provides an effective and flexible approach for describing surface shape variation in biomedical data.
  • LoCA outperforms existing methods by offering a controllable balance between localized and concise shape representations.
  • The method's formulation allows for intuitive interpretation of shape variations and captures complex properties like symmetry.