Dendritic spine detection using curvilinear structure detector and LDA classifier

Yong Zhang, Xiaobo Zhou, Rochelle M. Witt, Bernardo L. Sabatini, Donald Adjeroh, Stephen T.C. Wong

Research output: Contribution to journalArticlepeer-review

51 Scopus citations

Abstract

Dendritic spines are small, bulbous cellular compartments that carry synapses. Biologists have been studying the biochemical pathways by examining the morphological and statistical changes of the dendritic spines at the intracellular level. In this paper a novel approach is presented for automated detection of dendritic spines in neuron images. The dendritic spines are recognized as small objects of variable shape attached or detached to multiple dendritic backbones in the 2D projection of the image stack along the optical direction. We extend the curvilinear structure detector to extract the boundaries as well as the centerlines for the dendritic backbones and spines. We further build a classifier using Linear Discriminate Analysis (LDA) to classify the attached spines into valid and invalid types to improve the accuracy of the spine detection. We evaluate the proposed approach by comparing with the manual results in terms of backbone length, spine number, spine length, and spine density.

Original languageEnglish (US)
Pages (from-to)346-360
Number of pages15
JournalNeuroImage
Volume36
Issue number2
DOIs
StatePublished - Jun 2007

Keywords

  • Curvilinear structures
  • Dendritic spine
  • Fluorescence microscopy
  • Neurite outgrowth
  • Neuron image processing

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Fingerprint

Dive into the research topics of 'Dendritic spine detection using curvilinear structure detector and LDA classifier'. Together they form a unique fingerprint.

Cite this