Growcut-based drusen segmentation for age-related macular degeneration detection

Huiying Liu, Yanwu Xu, Damon W.K. Wong, Jiang Liu

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Age-related Macular Degeneration (AMD) is the third leading cause of blindness. Its prevalence is increasing in these years for the coming of 'aging time'. Early detection and grading can prohibit it from becoming severe and protect vision. The appearance of drusen is an important indicator for AMD thus automatic drusen detection and segmentation have attracted much research attention in the past years. In this paper, we propose a novel drusen segmentation method by using Growcut. This method first detects the local maximum and minimum points. The maximum points, which are potential drusen, are then classified as drusen or non-drusen. The drusen points will be used as foreground labels while the non-drusen points together with the minima will be used as background labels. These labels are fed into Growcut to obtain the drusen boundaries. The method is tested on a manually labeled dataset with 96 images containing drusen. The experimental results verify the effectiveness of the method.

Original languageEnglish
Title of host publication2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages161-164
Number of pages4
ISBN (Electronic)9781479961399
DOIs
Publication statusPublished - 27 Feb 2015
Externally publishedYes
Event2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014 - Valletta, Malta
Duration: 7 Dec 201410 Dec 2014

Publication series

Name2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014

Conference

Conference2014 IEEE Visual Communications and Image Processing Conference, VCIP 2014
Country/TerritoryMalta
CityValletta
Period7/12/1410/12/14

Keywords

  • Age-related Macular Degeneration
  • Drusen segmentation
  • Growcut

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Growcut-based drusen segmentation for age-related macular degeneration detection'. Together they form a unique fingerprint.

Cite this