AIMS: To determine if neural networks can detect diabetic features in fundus images and compare the network against an ophthalmologist screening a set of fundus images. METHODS: 147 diabetic and 32 normal images were captured from a fundus camera, stored on computer, and analysed using a back propagation neural network. The network was trained to recognise features in the retinal image. The effects of digital filtering techniques and different network variables were assessed. 200 diabetic and 101 normal images were then randomised and used to evaluate the network's performance for the detection of diabetic retinopathy against an ophthalmologist. RESULTS: Detection rates for the recognition of vessels, exudates, and haemorrhages were 91.7%, 93.1%, and 73.8% respectively. When compared with the results of the ophthalmologist, the 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 dependent upon preprocessing and the number of images used in training. When compared with the ophthalmologist, the network achieved good accuracy for the detection of diabetic retinopathy. The system could be used as an aid to the screening of diabetic patients for retinopathy.
AIMS: To determine if neural networks can detect diabetic features in fundus images and compare the network against an ophthalmologist screening a set of fundus images. METHODS: 147 diabetic and 32 normal images were captured from a fundus camera, stored on computer, and analysed using a back propagation neural network. The network was trained to recognise features in the retinal image. The effects of digital filtering techniques and different network variables were assessed. 200 diabetic and 101 normal images were then randomised and used to evaluate the network's performance for the detection of diabetic retinopathy against an ophthalmologist. RESULTS: Detection rates for the recognition of vessels, exudates, and haemorrhages were 91.7%, 93.1%, and 73.8% respectively. When compared with the results of the ophthalmologist, the 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 dependent upon preprocessing and the number of images used in training. When compared with the ophthalmologist, the network achieved good accuracy for the detection of diabetic retinopathy. The system could be used as an aid to the screening of diabeticpatients for retinopathy.
Authors: J A Pugh; J M Jacobson; W A Van Heuven; J A Watters; M R Tuley; D R Lairson; R J Lorimor; A S Kapadia; R Velez Journal: Diabetes Care Date: 1993-06 Impact factor: 19.112
Authors: V S Lee; R M Kingsley; E T Lee; M Lu; D Russell; N R Asal; R H Bradford; C P Wilkinson Journal: Ophthalmology Date: 1993-10 Impact factor: 12.079
Authors: Emanuele Trucco; Alfredo Ruggeri; Thomas Karnowski; Luca Giancardo; Edward Chaum; Jean Pierre Hubschman; Bashir Al-Diri; Carol Y Cheung; Damon Wong; Michael Abràmoff; Gilbert Lim; Dinesh Kumar; Philippe Burlina; Neil M Bressler; Herbert F Jelinek; Fabrice Meriaudeau; Gwénolé Quellec; Tom Macgillivray; Bal Dhillon Journal: Invest Ophthalmol Vis Sci Date: 2013-05-01 Impact factor: 4.799
Authors: George S Liu; Michael H Zhu; Jinkyung Kim; Patrick Raphael; Brian E Applegate; John S Oghalai Journal: Biomed Opt Express Date: 2017-09-20 Impact factor: 3.732