Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool.

By G. G. Gardner, D. Keating, T. Williamson, A. Elliott. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Retinal image analysis: concepts, applications and potential. (2006, background): “Gardner et al. (1996) employed a back propagation neural network to detect diabetic retinopathy features.”
Artificial intelligence in retina. (2018, methodology): “…myocardial infarction in patients presenting with anterior chest pain at an emergency department (Baxt, 1991), for diagnosing renal cancer from ultrasound (Maclin et al., 1991), or for screening of diabetic retinopathy based on features extracted from a fundus image (Gardner et al., 1996).”
A Computational-Intelligence-Based Approach for Detection of Exudates in Diabetic Retinopathy Images (2009, methodology): “Indeed, the reported lesion-based accuracies were often based on 10× 10 or 20× 20 patches (patch resolution) [8]–[10], and no pixel resolution validation was accomplished except in a couple of works [11], [12].”
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images (2017, background): “While ﬁrst approaches using neural networks to detect diabetic retinopathy on retinal images without additional feature extraction showed a low classiﬁcation accuracy [5, 6], recent approaches based on deep neural networks [7, 8, 9] report good performance.”
A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Gray-Level and Moment Invariants-Based Features (2011, background): “Gardner et al. [48] proposed a back propagation multilayer neural network (NN) for vascular tree segmentation.”
Automated microaneurysm detection using local contrast normalization and local vessel detection (2006, methodology): “An artificial neural network is also used by [8] to classify image regions as vessel, haemorrhage, or other lesion type.”
Automated feature extraction in color retinal images by a model based approach (2004, methodology): “Three strategies have been employed to the exudate detection: thresholding [3], [11], [12], edge detection [7], [13], and classification [14], [15].”
Retinal Imaging and Image Analysis (2010, unknown): “systems to detect exudates have been proposed [80], [85], [87],”
Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods (2008, background): “A number of techniques for icroaneurysm and haemorrhage detection have been proosed.”
Convolutional Neural Networks for Diabetic Retinopathy (2016, methodology): “Gardner et al used Neural Networks and pixel intensity values to achieve sensitivity and speciﬁcity results of 88.4% and 83.5% respectively for yes or no classiﬁcation of DR 16 .”