Membrane boundary extraction using circular multiple paths

Authors:
Changming Sun;Pascal Vallotton;Dadong Wang;Jamie Lopez;Yvonne Ng;David James
Affiliations:
CSIRO Mathematical and Information Sciences, Locked Bag 17, North Ryde, NSW 1670, Australia;CSIRO Mathematical and Information Sciences, Locked Bag 17, North Ryde, NSW 1670, Australia;CSIRO Mathematical and Information Sciences, Locked Bag 17, North Ryde, NSW 1670, Australia;Garvan Institute of Medical Research, 384 Victoria Street, Darlinghurst, Sydney, NSW 2010, Australia;Garvan Institute of Medical Research, 384 Victoria Street, Darlinghurst, Sydney, NSW 2010, Australia;Garvan Institute of Medical Research, 384 Victoria Street, Darlinghurst, Sydney, NSW 2010, Australia
Venue:
Pattern Recognition
Year:
2009

Citing 2
Cited 2

A fast algorithm for active contours and curvature estimation

CVGIP: Image Understanding
Multiple Paths Extraction in Images Using a Constrained Expanded Trellis

IEEE Transactions on Pattern Analysis and Machine Intelligence

Interactive segmentation of non-star-shaped contours by dynamic programming

Pattern Recognition
Computer-aided techniques for chromogenic immunohistochemistry: Status and directions

Computers in Biology and Medicine

Quantified Score

Hi-index	0.01

Visualization

Abstract

Membrane proteins represent over 50% of known drug targets. Accordingly, several widely used assays in the high content analysis area rely on quantitative measures of the translocation of proteins between intracellular organelles and the cell surface. In order to increase the sensitivity of these assays, one needs to measure the signal specifically along the membrane, requiring a precise segmentation of this compartment. Manual tracing of membrane boundary is very time-consuming and confronts us with issues of objectivity and reproducibility. In this paper, we present an approach based on a circular multiple paths technique on transformed images that enables us to segment the membrane compartment accurately and rapidly. We have presented three approaches for image transformation. The circular property of the multiple paths ensures that we are obtaining closed contours for the membrane boundary. The position of the multiple paths provides the edges of the membrane boundary. The effectiveness of our algorithm is illustrated using cells expressing epitope-tagged membrane proteins.