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

Neural cell classification by wavelets and multiscale curvature

R M Cesar Júnior1, L da F Costa

  • 1Department of Computer Science, IME, University of São Paulo, Brazil.

Biological Cybernetics
|November 27, 1998
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

Surface Morphology and Structural Modification Induced by Femtosecond Pulses in Hydrogenated Amorphous Silicon Films.

Journal of nanoscience and nanotechnology·2015
Same author

Neurodevelopmental and neuropsychiatric disorders represent an interconnected molecular system.

Molecular psychiatry·2013
Same author

Prominent effect of soil network heterogeneity on microbial invasion.

Physical review letters·2012
Same author

Knowledge acquisition by networks of interacting agents in the presence of observation errors.

Physical review. E, Statistical, nonlinear, and soft matter physics·2010
Same author

Epidemics in networks of spatially correlated three-dimensional root-branching structures.

Journal of the Royal Society, Interface·2010
Same author

Automatic contour extraction from 2D neuron images.

Journal of neuroscience methods·2008
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
Same journal

Geometric Learning Dynamics.

Biological cybernetics·2026
See all related articles

A novel multiscale approach accurately classifies retinal ganglion cells using wavelet transforms and shape descriptors like normalized multiscale wavelet energy (NMWE) and normalized multiscale bending energy (NMBE). This method achieves near 90% recognition rates for cat retinal ganglion cells.

Area of Science:

  • Biomedical Image Analysis
  • Computational Neuroscience
  • Pattern Recognition

Background:

  • Accurate classification of neural cells is crucial for understanding visual processing.
  • Existing methods for characterizing cell morphology may lack the necessary detail or computational efficiency.

Purpose of the Study:

  • To introduce and evaluate a novel multiscale approach for automatic classification of retinal ganglion cells.
  • To compare the efficacy of normalized multiscale wavelet energy (NMWE) and normalized multiscale bending energy (NMBE) as shape descriptors.

Main Methods:

  • Utilized continuous wavelet transform to generate a W-representation of cell contours.
  • Calculated normalized multiscale wavelet energy (NMWE) and normalized multiscale bending energy (NMBE) from cell shapes.

Related Experiment Videos

  • Employed feature ordering and statistical classifiers (minimum-distance, k-nearest neighbours, maximum likelihood) for classification.

    • Main Results:

    • Both NMWE and NMBE demonstrated suitability for shape classification with similar performance.
    • NMBE showed a slightly higher recognition rate, while NMWE was less computationally intensive.
    • Achieved mean recognition rates near 90% for classifying cat retinal ganglion cells (alpha and beta cells).

    Conclusions:

    • The proposed multiscale shape analysis technique provides a robust framework for neural cell description and classification.
    • This methodology shows potential for broader applications in biological shape characterization and biomedical image analysis.
    • The multiscale energy measures align well with human subjective assessments of shape complexity.