Share Email Print
cover

Proceedings Paper

Automatic detection of diabetic retinopathy features in ultra-wide field retinal images
Author(s): Anastasia Levenkova; Arcot Sowmya; Michael Kalloniatis; Angelica Ly; Arthur Ho
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Diabetic retinopathy (DR) is a major cause of irreversible vision loss. DR screening relies on retinal clinical signs (features). Opportunities for computer-aided DR feature detection have emerged with the development of Ultra-WideField (UWF) digital scanning laser technology. UWF imaging covers 82% greater retinal area (200°), against 45° in conventional cameras3 , allowing more clinically relevant retinopathy to be detected4 . UWF images also provide a high resolution of 3078 x 2702 pixels. Currently DR screening uses 7 overlapping conventional fundus images, and the UWF images provide similar results1,4. However, in 40% of cases, more retinopathy was found outside the 7-field ETDRS) fields by UWF and in 10% of cases, retinopathy was reclassified as more severe4 . This is because UWF imaging allows examination of both the central retina and more peripheral regions, with the latter implicated in DR6 . We have developed an algorithm for automatic recognition of DR features, including bright (cotton wool spots and exudates) and dark lesions (microaneurysms and blot, dot and flame haemorrhages) in UWF images. The algorithm extracts features from grayscale (green “red-free” laser light) and colour-composite UWF images, including intensity, Histogram-of-Gradient and Local binary patterns. Pixel-based classification is performed with three different classifiers. The main contribution is the automatic detection of DR features in the peripheral retina. The method is evaluated by leave-one-out cross-validation on 25 UWF retinal images with 167 bright lesions, and 61 other images with 1089 dark lesions. The SVM classifier performs best with AUC of 94.4% / 95.31% for bright / dark lesions.

Paper Details

Date Published: 3 March 2017
PDF: 8 pages
Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101341M (3 March 2017); doi: 10.1117/12.2253980
Show Author Affiliations
Anastasia Levenkova, The Univ. of New South Wales (Australia)
Arcot Sowmya, The Univ. of New South Wales (Australia)
Michael Kalloniatis, The Univ. of New South Wales (Australia)
Ctr. for Eye Health Ltd. (Australia)
Angelica Ly, The Univ. of New South Wales (Australia)
Ctr. for Eye Health Ltd. (Australia)
Arthur Ho, The Univ. of New South Wales (Australia)
Brien Holden Vision Institute (Australia)


Published in SPIE Proceedings Vol. 10134:
Medical Imaging 2017: Computer-Aided Diagnosis
Samuel G. Armato; Nicholas A. Petrick, Editor(s)

© SPIE. Terms of Use
Back to Top