AUTOMATIC DETECTION OF DIABETIC-RETINOPATHY USING AN ARTIFICIAL NEURAL-NETWORK - A SCREENING TOOL

Aims - To determine if neural networks can detect diabetic features in fundus images and compare the network against an ophthalmologist scre ening a set of fundus images. Methods - 147 diabetic and 32 normal ima ges were captured from a fundus camera, stored on computer, and analys ed using a back propagation neural network. The network was trained to recognise features in the retinal image. The effects of digital filte ring techniques and different network variables were assessed. 200 dia betic and 101 normal images were then randomised and used to evaluate the network's performance for the detection of diabetic retinopathy ag ainst an ophthalmologist. Results - Detection rates for the recognitio n of vessels, exudates, and haemorrhages were 91.7%, 93.1%, and 73.8% respectively. When compared with the results of the ophthalmologist, t he network achieved a sensitivity of 88.4% and a specificity of 83.5% for the detection of diabetic retinopathy. Conclusions - Detection of vessels, exudates, and haemorrhages was possible, with success rates d ependent upon pre-processing and the number of images used in training . When compared with the ophthalmologist, the network achieved good ac curacy for the detection of diabetic retinopathy. The system could be used as an aid to the screening of diabetic patients for retinopathy.