University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Segmentation and Shape Classification of Nuclei in DAPI Images

Snell, V, Kittler, J and Christmas, W (2011) Segmentation and Shape Classification of Nuclei in DAPI Images In: The 22nd British Machine Vision Conference, 2011-08-29 - 2011-09-02, University of Dundee.

[img]
Preview
PDF
snell.pdf
Available under License : See the attached licence file.

Download (245Kb)
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf

Download (32Kb)

Abstract

This paper addresses issues of analysis of DAPI-stained microscopy images of cell samples, particularly classification of objects as single nuclei, nuclei clusters or nonnuclear material. First, segmentation is significantly improved compared to Otsu’s method[5] by choosing a more appropriate threshold, using a cost-function that explicitly relates to the quality of resulting boundary, rather than image histogram. This method applies ideas from active contour models to threshold-based segmentation, combining the local image sensitivity of the former with the simplicity and lower computational complexity of the latter. Secondly, we evaluate some novel measurements that are useful in classification of resulting shapes. Particularly, analysis of central distance profiles provides a method for improved detection of notches in nuclei clusters. Error rates are reduced to less than half compared to those of the base system, which used Fourier shape descriptors alone.

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Depositing User: Symplectic Elements
Date Deposited: 24 Feb 2012 17:01
Last Modified: 23 Sep 2013 18:58
URI: http://epubs.surrey.ac.uk/id/eprint/74810

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800