Automated neurite extraction using dynamic programming for high-throughput screening of neuron-based assays

Yong Zhang, Xiaobo Zhou, Alexei Degterev, Marta Lipinski, Donald Adjeroh, Junying Yuan, Stephen T.C. Wong

Research output: Contribution to journalArticlepeer-review

37 Scopus citations


High-throughput screening (HTS) of cell-based assays has recently emerged as an important tool of drug discovery. The analysis and modeling of HTS microscopy neuron images, however, is particularly challenging. In this paper we present a novel algorithm for extraction and quantification of neurite segments from HTS neuron images. The algorithm is designed to be able to detect and link neurites even with complex neuronal structures and of poor imaging quality. Our proposed algorithm automatically detects initial seed points on a set of grid lines and estimates the ending points of the neurite by iteratively tracing the centerline points along the line path representing the neurite segment. The live-wire method is then applied to link the seed points and the corresponding ending points using dynamic programming techniques, thus enabling the extraction of the centerlines of the neurite segments accurately and robustly against noise, discontinuity, and other image artifacts. A fast implementation of our algorithm using dynamic programming is also provided in the paper. Any thin neurite and its segments with low intensity contrast can be well preserved by detecting the starting and ending points of the neurite. All these properties make the proposed algorithm attractive for high-throughput screening of neuron-based assays.

Original languageEnglish (US)
Pages (from-to)1502-1515
Number of pages14
Issue number4
StatePublished - May 1 2007


  • Automatic neurite tracing
  • Dynamic programming
  • High-throughput screening
  • Line structures
  • Neurite extraction
  • Neuron image analysis

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology


Dive into the research topics of 'Automated neurite extraction using dynamic programming for high-throughput screening of neuron-based assays'. Together they form a unique fingerprint.

Cite this