Algorithms for digital image processing in diabetic retinopathy

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

doi:10.1016/j.compmedimag.2009.06.003

« Previous Next »Computerized Medical Imaging and Graphics
Volume 33, Issue 8 , Pages 608-622, December 2009

Algorithms for digital image processing in diabetic retinopathy

R.J. Winder
- Health and Rehabilitation Sciences Research Institute, University of Ulster, Shore Road, Newtownabbey BT37 0QB, United Kingdom
- Corresponding author. Tel.: +44 2890368440; fax: +44 2890368068.
P.J. Morrow
- School of Computing and Information Engineering, University of Ulster, Cromore Road, Coleraine BT52 1SA, United Kingdom
I.N. McRitchie
- Health and Rehabilitation Sciences Research Institute, University of Ulster, Shore Road, Newtownabbey BT37 0QB, United Kingdom
J.R. Bailie
- Health and Social Care Research and Development Office, 12 – 22 Linenhall Street, Belfast BT2 8BS, United Kingdom
P.M. Hart
- Northern Ireland Diabetic Retinopathy Screening Service, Belfast Health and Social Care Trust, Royal Group of Hospitals, Grosvenor Road, Belfast BT12 6BA, United Kingdom

Received 9 April 2009; received in revised form 1 June 2009; accepted 22 June 2009.

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.

Keywords: Diabetic retinopathy, Computer-aided diagnosis, Digital imaging, Image processing