Drusen detection based on Scale-space with Feature Stability

C Duanggate; B Uyyanonvara; S Makhanov; S A Barman; T Williamson

Drusen detection based on Scale-space with Feature Stability

C Duanggate, B Uyyanonvara, S Makhanov, S A Barman, T Williamson

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper proposes a novel segmentation technique for drusen detection in retinal fundus images based on the scale space approach endowed with feature stability. To select significant blobs representing drusen, the stability of the features of scale-space blobs is taken into account in addition to conventional blobs' lifetime. The algorithm was tested with over 20,000 blobs from 26 retinal images and the results show that the method can detect variable size and variable shape drusen efficiently with Positive Predictive Value over 95%.

Original language	English
Publication status	Published - Jul 2011
Event	Medical Image Analysis and Understanding MIUA 2011 - London, United Kingdom Duration: 14 Jul 2011 → 15 Jul 2011

Conference

Conference	Medical Image Analysis and Understanding MIUA 2011
Period	14/07/11 → 15/07/11

Keywords

Allied health professions and studies

Cite this

@conference{63d54fb46f3840028ba4039900cfbac9,

title = "Drusen detection based on Scale-space with Feature Stability",

abstract = "This paper proposes a novel segmentation technique for drusen detection in retinal fundus images based on the scale space approach endowed with feature stability. To select significant blobs representing drusen, the stability of the features of scale-space blobs is taken into account in addition to conventional blobs' lifetime. The algorithm was tested with over 20,000 blobs from 26 retinal images and the results show that the method can detect variable size and variable shape drusen efficiently with Positive Predictive Value over 95\%.",

keywords = "Allied health professions and studies",

author = "C Duanggate and B Uyyanonvara and S Makhanov and Barman, \{S A\} and T Williamson",

year = "2011",

month = jul,

language = "English",

note = "Medical Image Analysis and Understanding MIUA 2011 ; Conference date: 14-07-2011 Through 15-07-2011",

}

TY - CONF

T1 - Drusen detection based on Scale-space with Feature Stability

AU - Duanggate, C

AU - Uyyanonvara, B

AU - Makhanov, S

AU - Barman, S A

AU - Williamson, T

PY - 2011/7

Y1 - 2011/7

N2 - This paper proposes a novel segmentation technique for drusen detection in retinal fundus images based on the scale space approach endowed with feature stability. To select significant blobs representing drusen, the stability of the features of scale-space blobs is taken into account in addition to conventional blobs' lifetime. The algorithm was tested with over 20,000 blobs from 26 retinal images and the results show that the method can detect variable size and variable shape drusen efficiently with Positive Predictive Value over 95%.

AB - This paper proposes a novel segmentation technique for drusen detection in retinal fundus images based on the scale space approach endowed with feature stability. To select significant blobs representing drusen, the stability of the features of scale-space blobs is taken into account in addition to conventional blobs' lifetime. The algorithm was tested with over 20,000 blobs from 26 retinal images and the results show that the method can detect variable size and variable shape drusen efficiently with Positive Predictive Value over 95%.

KW - Allied health professions and studies

UR - http://www.biomedical-image-analysis.co.uk/index.php/on-line-proceedings

M3 - Paper

T2 - Medical Image Analysis and Understanding MIUA 2011

Y2 - 14 July 2011 through 15 July 2011

ER -

Drusen detection based on Scale-space with Feature Stability

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this