Automated segmentation and tracking of dynamic focal adhesions in time-lapse fluorescence microscopy

  • Authors:
  • Guannan Li;Nasir Rajpoot

  • Affiliations:
  • Computational Biology & Bioimaging (COMBI), Department of Computer Science, University of Warwick, United Kingdom;Computational Biology & Bioimaging (COMBI), Department of Computer Science, University of Warwick, United Kingdom

  • Venue:
  • ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Focal adhesions are sub-cellular macromolecules that play essential roles in many important biological events including cell motility, cell proliferation, cell differentiation, regulation of gene expression and cell survival. Fluorescence microscopy imaging of focal adhesions is the primary method used to understand focal adhesion dynamics. Data acquisition for the focal adhesion dynamics is generally done by manual segmentation and tracking of focal adhesion. The performance of manual work can be significantly hurt by the long time required in large data set. Also manual segmentation and tracking are highly laborious and time consuming. In this paper, a system is presented for automated segmenting and tracking of focal adhesion molecules. The system leverages several image processing approaches in the segmentation process and focal adhesions can be successfully recognized in each image frame. We also present a novel object tracking algorithm which can be used to track the dynamics of focal adhesion molecules in the image sequences.