Lincoln Repository

Menu

A robust lesion boundary segmentation algorithm using level set methods

Massey, Elizabeth, Hunter, Andrew, 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.

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

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.
  • Format: PDF
  • Repository staff only
  • Size: 150kB
A robust lesion boundary segmentation algorithm using level set methods
Pre-print
  • Format: PDF
  • Size: 128kB
[img]
[Download]
[img] PDF (4 pages)
LS_WC2009.pdf
Restricted to Repository staff only
150kB
[img]
Preview
 PDF
WC2009-1569197186.pdf
128kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

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.

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 On:15 Jan 2010 10:16

Repository Staff Only: item control page