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

Recognition of regions in brain sections.

A Waks1, O J Tretiak

  • 1Image Processing Center, Drexel University, Philadelphia, PA 19104.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|September 1, 1990
PubMed
Summary

This study presents a robust system for identifying and tracking brain region boundaries in sequential sections, even with blurred or missing outlines. The efficient dynamic programming approach ensures accurate results in challenging neuroimaging data.

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

Fluorescence imaging for machine vision.

Applied optics·2010
Same author

Region-specific tritium enrichment, and not differential beta-absorption, is the major cause of 'quenching' in film autoradiography.

Physics in medicine and biology·1997
Same author

Multimodality multidimensional image analysis of cortical and subcortical plasticity in the rat brain.

Annals of biomedical engineering·1996
Same author

Three-dimensional reconstruction of activated columns from 2-[14C]deoxy-D-glucose data.

NeuroImage·1995
Same author

Numerical solution of the direct scattering problem through the transformed acoustical wave equation.

The Journal of the Acoustical Society of America·1992
Same author

Computation of the far-field time domain solution of the scattering problem.

The Journal of the Acoustical Society of America·1992

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Medical Image Analysis

Background:

  • Accurate identification of brain regions in sequential sections is crucial for neuroimaging analysis.
  • Brain region boundaries present challenges due to blur, missing information, and non-stationarity.
  • Existing methods may struggle with noise, outliers, and indistinct region characteristics.

Purpose of the Study:

  • To develop a robust and efficient system for region identification and boundary tracking in sequential brain sections.
  • To address challenges posed by blurred, missing, or noisy boundaries in neuroimaging data.
  • To improve the accuracy and reliability of brain region segmentation.

Main Methods:

  • Region segmentation formulated as a multi-hypothesis test to maximize a performance criterion.

Related Experiment Videos

  • Adaptive search area around reference boundaries from previous sections for efficiency.
  • Fast first-order dynamic programming (DP) for boundary candidate evaluation.
  • Integrated outlier rejection techniques within the multi-hypothesis test framework.

    • Main Results:

    • The developed algorithm successfully traces brain region boundaries even with low contrast and missing outline segments.
    • Demonstrated robustness in handling noise and outliers inherent in neuroimaging data.
    • Achieved efficient processing through dynamic programming and adaptive search strategies.

    Conclusions:

    • The proposed system offers a reliable method for brain region boundary detection in challenging sequential sections.
    • The integration of dynamic programming and outlier rejection enhances segmentation accuracy and efficiency.
    • This approach advances the analysis of neuroimaging data where region boundaries are indistinct or compromised.