Cell segmentation using Hessian-based detection and contour evolution with directional derivatives

I Ersoy; F Bunyak; M. A Mackey; K Palaniappan

doi:10.1109/ICIP.2008.4712127

Back

Conference proceeding

Cell segmentation using Hessian-based detection and contour evolution with directional derivatives

I Ersoy, F Bunyak, M. A Mackey and K Palaniappan

2008 15th IEEE International Conference on Image Processing, Vol.2008, pp.1804-1807

10/2008

DOI: 10.1109/ICIP.2008.4712127

PMCID: PMC2743148

PMID: 19756203

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/2743148View

Open Access

Abstract

The large amount of data produced by biological live cell imaging studies of cell behavior requires accurate automated cell segmentation algorithms for rapid, unbiased and reproducible scientific analysis. This paper presents a new approach to obtain precise boundaries of cells with complex shapes using ridge measures for initial detection and a modified geodesic active contour for curve evolution that exploits the halo effect present in phase-contrast microscopy. The level set contour evolution is controlled by a novel spatially adaptive stopping function based on the intensity profile perpendicular to the evolving front. The proposed approach is tested on human cancer cell images from LSDCAS and achieves high accuracy even in complex environments.

active contour

Active contours

Algorithm design and analysis

biomedical image processing

cell segmentation

Cells (biology)

Evolution (biology)

Image analysis

Image segmentation

Level measurement

level sets

Phase detection

Phase measurement

ridge detection

Shape measurement

Details

Title: Subtitle: Cell segmentation using Hessian-based detection and contour evolution with directional derivatives
Creators: I Ersoy - University of Missouri
F Bunyak - University of Missouri
M. A Mackey - University of Iowa
K Palaniappan - University of Missouri
Resource Type: Conference proceeding
Publication Details: 2008 15th IEEE International Conference on Image Processing, Vol.2008, pp.1804-1807
DOI: 10.1109/ICIP.2008.4712127
PMID: 19756203
PMCID: PMC2743148
NLM abbreviation: Proc Int Conf Image Proc
ISSN: 1522-4880
eISSN: 2381-8549
Publisher: IEEE
Language: English
Date published: 10/2008
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology
Record Identifier: 9984196974902771

Metrics

68 Record Views

25 Times Cited - Web of Science