Algorithms for digital image processing in diabetic retinopathy

John Winder, Philip Morrow, I. N. McRitchie, J. R. Bailie, P. M. Hart

Research output: Contribution to journalArticle

145 Citations (Scopus)

Abstract

This work examined recent literature on digital image processing in the field of diabetic retinopathy. Algorithms were categorized into 5 steps (preprocessing; localization and segmentation of the optic disk; segmentation of the retinal vasculature; localization of the macula and fovea; localization and segmentation of retinopathy). The variety of outcome measures, use of a gold standard or ground truth, data sample sizes and the use of image databases is discussed. It is intended that our classification of algorithms into a small number of categories, definition of terms and discussion of evolving techniques will provide guidance to algorithm designers for diabetic retinopathy. (C) 2009 Elsevier Ltd. All rights reserved.
LanguageEnglish
Pages608-622
JournalComputerized Medical Imaging and Graphics
Volume33
Issue number8
DOIs
Publication statusPublished - Dec 2009

Fingerprint

Image processing
Optics

Keywords

  • Diabetic retinopathy
  • Computer-aided diagnosis
  • Digital imaging
  • Image processing

Cite this

Winder, John ; Morrow, Philip ; McRitchie, I. N. ; Bailie, J. R. ; Hart, P. M. / Algorithms for digital image processing in diabetic retinopathy. In: Computerized Medical Imaging and Graphics. 2009 ; Vol. 33, No. 8. pp. 608-622.
@article{64447d90437543b7b00d354ebdd21c3f,
title = "Algorithms for digital image processing in diabetic retinopathy",
abstract = "This work examined recent literature on digital image processing in the field of diabetic retinopathy. Algorithms were categorized into 5 steps (preprocessing; localization and segmentation of the optic disk; segmentation of the retinal vasculature; localization of the macula and fovea; localization and segmentation of retinopathy). The variety of outcome measures, use of a gold standard or ground truth, data sample sizes and the use of image databases is discussed. It is intended that our classification of algorithms into a small number of categories, definition of terms and discussion of evolving techniques will provide guidance to algorithm designers for diabetic retinopathy. (C) 2009 Elsevier Ltd. All rights reserved.",
keywords = "Diabetic retinopathy, Computer-aided diagnosis, Digital imaging, Image processing",
author = "John Winder and Philip Morrow and McRitchie, {I. N.} and Bailie, {J. R.} and Hart, {P. M.}",
year = "2009",
month = "12",
doi = "10.1016/j.compmedimag.2009.06.003",
language = "English",
volume = "33",
pages = "608--622",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier",
number = "8",

}

Algorithms for digital image processing in diabetic retinopathy. / Winder, John; Morrow, Philip; McRitchie, I. N.; Bailie, J. R.; Hart, P. M.

In: Computerized Medical Imaging and Graphics, Vol. 33, No. 8, 12.2009, p. 608-622.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Algorithms for digital image processing in diabetic retinopathy

AU - Winder, John

AU - Morrow, Philip

AU - McRitchie, I. N.

AU - Bailie, J. R.

AU - Hart, P. M.

PY - 2009/12

Y1 - 2009/12

N2 - This work examined recent literature on digital image processing in the field of diabetic retinopathy. Algorithms were categorized into 5 steps (preprocessing; localization and segmentation of the optic disk; segmentation of the retinal vasculature; localization of the macula and fovea; localization and segmentation of retinopathy). The variety of outcome measures, use of a gold standard or ground truth, data sample sizes and the use of image databases is discussed. It is intended that our classification of algorithms into a small number of categories, definition of terms and discussion of evolving techniques will provide guidance to algorithm designers for diabetic retinopathy. (C) 2009 Elsevier Ltd. All rights reserved.

AB - This work examined recent literature on digital image processing in the field of diabetic retinopathy. Algorithms were categorized into 5 steps (preprocessing; localization and segmentation of the optic disk; segmentation of the retinal vasculature; localization of the macula and fovea; localization and segmentation of retinopathy). The variety of outcome measures, use of a gold standard or ground truth, data sample sizes and the use of image databases is discussed. It is intended that our classification of algorithms into a small number of categories, definition of terms and discussion of evolving techniques will provide guidance to algorithm designers for diabetic retinopathy. (C) 2009 Elsevier Ltd. All rights reserved.

KW - Diabetic retinopathy

KW - Computer-aided diagnosis

KW - Digital imaging

KW - Image processing

U2 - 10.1016/j.compmedimag.2009.06.003

DO - 10.1016/j.compmedimag.2009.06.003

M3 - Article

VL - 33

SP - 608

EP - 622

JO - Computerized Medical Imaging and Graphics

T2 - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 8

ER -