A robust lesion boundary segmentation algorithm using level set methods

Massey, Elizabeth and Hunter, Andrew and Lowell, James and Steel, David (2009) A robust lesion boundary segmentation algorithm using level set methods. In: World Congress on Medical Physics and Biomedical Engineering , September 7 - 12, 2009 , Munich, Germany.

Documents
A robust lesion boundary segmentation algorithm using level set methods
This paper addresses the issue of accurate lesion segmentation in retinal imagery, using level set methods and a novel stopping mechanism - an elementary features scheme. Specifically, the curve propagation is guided by a gradient map built using a combination of histogram equalization and robust statistics. The stopping mechanism uses elementary features gathered as the curve deforms over time, and then using a ‘lesionness’ measure, defined herein, ’looks back in time’ to find the point at which the curve best fits the real object. We compare the proposed method against five other segmentation algorithms performed on 50 randomly selected images of exudates with a database of clinician demarcated boundaries as ground truth.
[img]
[Download]
Request a copy
A robust lesion boundary segmentation algorithm using level set methods
Pre-print
[img]
[Download]
[img] PDF (4 pages)
LS_WC2009.pdf
Restricted to Repository staff only

150kB
[img]
Preview
PDF
WC2009-1569197186.pdf

128kB

Full text URL: http://dx.doi.org/10.1007/978-3-642-03891-4_81

Abstract

This paper addresses the issue of accurate lesion segmentation in retinal imagery, using level set methods and
a novel stopping mechanism - an elementary features scheme. Specifically, the curve propagation is guided
by a gradient map built using a combination of histogram equalization and robust statistics. The stopping
mechanism uses elementary features gathered as the curve deforms over time, and then using a lesionness
measure, defined herein, ’looks back in time’ to find the point at which the curve best fits the real object.
We compare the proposed method against five other
segmentation algorithms performed on 50 randomly selected images of exudates with a database of clinician
demarcated boundaries as ground truth.

Item Type:Conference or Workshop Item (Paper)
Additional Information:This paper addresses the issue of accurate lesion segmentation in retinal imagery, using level set methods and a novel stopping mechanism - an elementary features scheme. Specifically, the curve propagation is guided by a gradient map built using a combination of histogram equalization and robust statistics. The stopping mechanism uses elementary features gathered as the curve deforms over time, and then using a lesionness measure, defined herein, ’looks back in time’ to find the point at which the curve best fits the real object. We compare the proposed method against five other segmentation algorithms performed on 50 randomly selected images of exudates with a database of clinician demarcated boundaries as ground truth.
Keywords:Retinal Image Analysis, Segmentation, Level Sets
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:2131
Deposited By:INVALID USER
Deposited On:15 Jan 2010 10:16
Last Modified:13 Mar 2013 08:34

Repository Staff Only: item control page