Automated detection of diabetic retinopathy on digital fundus images

Sinthanayothin, Chanjira; Boyce, J.F.; Williamson, Tom H.; Cook, Helen; Mensah, Evelyn; Lal, Sadhna; Usher, David

doi:10.1046/j.1464-5491.2002.00613.x

Cited by 450 publications

(232 citation statements)

References 17 publications

Supporting

Mentioning

223

Contrasting

Unclassified

Order By: Relevance

“…Further possibilities offered by digital imaging include stereo imaging [67] and telemedicine [68]. Algorithms for automated photographic reading could possibly reach acceptable sensitivity (78-88%) and specificity (84-100%) in detecting different lesions of retinopathy, as compared to an ophthalmologist [69,70], opening the way to computer-assisted grading. As a main problem with medical image interpretation is the rapid deterioration of graders' concentration with increasing workloads, this prospect will become a viable option in mass screening for STDR.…”

Section: Methodsmentioning

confidence: 99%

Diabetic retinopathy

2002

View full text Add to dashboard Cite

Abstract. Easy observation of the fundus oculi makes retinopathy the most frequently reported chronic complication of diabetes and, consequently, the one we know best in terms of epidemiology and natural history. Achieving near-normal levels of blood glucose and blood pressure provides empirical though powerful tools for clinicians to delay the onset and progression of diabetic retinopathy. Even when these measures have failed and retinopathy becomes sight-threatening, laser photocoagulation has proven remarkably effective. Nonetheless, retinopathy remains a leading cause of blindness and there is little evidence that diabetes-related visual loss is decreasing in industrialized countries. This may result from the mixed blessing of prolonged survival of patients who had become diabetic when metabolic control was pursued less fastidiously than today. Screening for sight-threatening retinopathy is the most cost-effective medical procedure known and should help optimise the use of diagnostic and therapeutic resources, but its widest deployment still meets with inertia and lack of interest within most health care systems. Improving clinical skills and technology, however, allow us to take a more optimistic look at the future, as pathogenesis-targeted forms of treatment are being developed and tested through appropriately powered clinical trials. [Diabetologia (2002[Diabetologia ( ) 45:1617[Diabetologia ( -1634

show abstract

Section: Methodsmentioning

confidence: 99%

Diabetic retinopathy

2002

View full text Add to dashboard Cite

show abstract

“…In particular in ophthalmology photos of the eye background are used by medical experts to diagnose and document diseases like glaucoma or diabetic retinopathy. In addition the images are commonly further evaluated by automatic software tools to support the diagnosis [1][2][3].…”

Section: Motivationmentioning

confidence: 99%

Automated quality assessment of retinal fundus photos

Paulus¹,

Meier²,

Bock³

et al. 2010

Int J CARS

View full text Add to dashboard Cite

“…It is an important step in screening programs for early detection of diabetic retinopathy [1], registration of retinal images for treatment evaluation [2] (to follow the evaluation of some lesions over time or to compare images obtained under different conditions), generating retinal map for diagnosis and treatment of age-related macular degeneration [3], or locating the optic disc and the fovea [4].…”

Section: Introductionmentioning

confidence: 99%

“…Unsupervised methods in the literature comprise the matched filter responses, edge detectors, grouping of edge pixels, model based locally adaptive thresholding, vessel tracking, topology adaptive snakes, and morphology-based techniques [5]. Supervised methods, which require feature vector for each pixel and manually labelled images for training, are the most recent approaches in vessel segmentation and use the neural networks [1], or the K-nearest neighbour classifier [5,6] for classifying image pixels as blood vessel or nonblood vessel pixels. These methods depend on generating a feature vector for every pixel in the image and then using training samples (with known classes) to design a classifier to classify these training samples into their corresponding classes.…”

Section: Introductionmentioning

confidence: 99%