Table 1 - uploaded by Mahi Muqit
Content may be subject to copyright.
Source publication
Contexts in source publication
Context 3
... identification of the DR severity level of an eye allows a prediction of risk of DR progression, visual loss, and determination of appropriate treatment recommendations including follow-up interval. Annex Table 1 details the signs associated with DR. ...
Context 4
... stages of DR, from nonproliferative to proliferative DR, can be categorized using the simple International Classification of DR scale shown in Table 1. ...
Context 5
... stages of DR can be classified using the International Classification of DR Scale shown in Table 1. Based on this Classification, referral decision can be used in high resource settings (Table 2a), and low-/intermediate settings (Table 2b). ...
Context 6
... If DR can be classified according to the simplified International Classification of DR (Table 1), they should be referred accordingly (Table 2a and Table 2b). ...
Similar publications
Diabetes technologies such as continuous glucose monitoring (CGM) continue to evolve at an increasingly rapid pace. Seventeen new CGM devices have been introduced to the market during the past decade. The introduction of each new system is supported by well-designed randomized controlled trials and real-world retrospective and prospective studies....
Citations
... The International Council of Ophthalmology (ICO) and IDF identified retinal photography as the gold standard in DRS, largely preferred for its objective imaging and provision of a permanent record [2,10]. The Society for Endocrinology, Metabolism and Diabetes of South Africa (SEMDSA) further recommended that the ideal screening person should be an ophthalmologist or optometrist trained in detecting DR [7]. ...
Diabetic retinopathy is a vascular disease of the retina that affects patients with uncontrolled diabetes. Untreated diabetic retinopathy (DR) can eventually lead to blindness. To date, diabetic retinopathy is the third leading cause of vision loss in the working class globally. Frequent retinal screening for all diabetic people is an effective method of preventing diabetic retinopathy blindness. This has relied on the use of ophthalmologists, but due to scarce resources, such as a shortage of human resources for eye health, this has denied many patients quality eye health care in a resource-limited setting. The recent advances on the use of teleophthalmology are promising to close this gap. This study aimed to map available evidence on the use of teleophthalmology in the screening of DR globally and to explore how this can be used to complement short-staffed eye clinics, especially in resource-constrained contexts. Studies were sourced from Google Scholar, PubMed, Science Direct, and EBSCO host. The final study selection was presented using a PRISMA chart. The mixed method appraisal tool was used to assess the quality of the nine studies included. The random effect model was used to estimate pooled prevalence estimates. Levels of heterogeneity were evaluated using Cochran's Q statistic and I2. Of nine included studies, eight were from high-income countries. The screening was performed at the primary healthcare level in eight of nine included studies. Only one study used a mydriatic agent, and the commonly used fundus camera was the non-mydriatic fundus camera. The overall estimated pooled prevalence of DR was 29 (95%CI: 10-34). Teleophthalmology at the primary health care level showed that early intervention in diabetic retinopathy reduced avoidable blindness and ensured remote access to eye health professionals, thus alleviating the burden on them.
... According to the International Classification of Diabetic Retinopathy (ICDR), International Council of Ophthalmology (ICO) Guidelines for Diabetic Eye Care 2017, DR stages can be classified into 5 grades: no DR, mild NPDR, moderate NPDR, severe NPDR, and PDR (20). In this study, referable diabetic retinopathy (RDR) was defined as moderate NPDR, severe NPDR, and PDR (21), while none referable diabetic retinopathy (NRDR) was defined as fundus photographs of no DR(normal or other diseases) and mild NPDR. ...
... According to the ICDR, DME is defined as any hard exudates within a one-disc diameter of the fovea or an area of hard exudates in the macular area that encompassed at least 50% of the disc area. OCT was considered the most sensitive method to identify DME and also provide a quantitative assessment of DME in determining DME severity (20). Unlike OCT, the definition of DME depending on fundus image is kind of out of date. ...
Background:
This study aimed to establish and evaluate an artificial intelligence-based deep learning system (DLS) for automatic detection of diabetic retinopathy. This could be important in developing an advanced tele-screening system for diabetic retinopathy.
Methods:
A DLS with a convolutional neural network was developed to recognize fundus images of referable diabetic retinopathy. A total data set of 41,866 color fundus images were obtained from 17 cities in the Yangtze River Delta Urban Agglomeration (YRDUA). Five experienced retinal specialists and 15 ophthalmologists were recruited to verify images. For training, 80% of the data set was used, and the other 20% served as the validation data set. To effectively understand the learning process, the DLS automatically superimposed a heatmap on the original image. The regions utilized by the DLS were highlighted for diagnosis.
Results:
Using the local validation data set, the DLS achieved an area under the curve of 0.9824. Based on the manual screening criteria, an operating point was set at about 0.9 sensitivity to evaluate the DLS. Specificity was recorded at 0.9609 and sensitivity was 0.9003. The DLSs showed excellent reliability, repeatability, and high efficiency. After analyzing the misclassification, it was found that 88.6% of the false-positives were mild non-proliferative diabetic retinopathy (NPDR) whereas, 81.6% of the false-negatives were intraretinal microvascular abnormalities.
Conclusions:
The DLS efficiently detected fundus images from complex sources in the real world. Incorporating DLS technology in tele-screening will advance the current screening programs to offer a cost-effective and time-efficient solution for detecting diabetic retinopathy.
... For the software part, we used the programming language Python and the NumPy [18] library and SciPy [19]. To standardize the image, we had to add a mask to define the boundaries of the eye itself in order to exclude irrelevant pixels, for greater efficiency, we ourselves wrote the program element that automatically defines the image boundary. ...
Described for the first time by MacKenzie (1879), diabetic retinopathy (DR) and today is the most common cause of blindness among persons of working age in most countries of the world. Prevention of DR is the early detection of a violation of morphology and a deterioration in the light sensitivity of the retina associated with this disease. To do this, highly informative methods of non-invasive retinal research are needed, with predictive capabilities. In this article, we propose an autonomous algorithm for such diagnostics, based on the training of the Artificial Neural Network (ANN) and the preprocessing of the image by an anisotropic diffusion filter. It allows not only to detect pathologies moreover to provide them with probabilistic evaluation of a possible variant of the disease.
The diabetic retinopathy is a vital factor of vision loss among individuals with diabetes. Early detection of this condition has significant importance for the patient’s vision. In this proposed work, neural network architectures are implemented by considering the existing methods as base methods and developed a model which is unique for detection of diabetic retinopathy among diabetic patients by screening the fundus images through the proposed models. Timely detection and appropriate treatment can help to prevent the beginning and development of diabetic retinopathy among diabetic patients. Accurate detection of the disease is an essential requirement in the health domain. Our focus of the research is to classify the severity level using multiclass classification for diabetic retinopathy. The classification results, executed on the Google Colaboratory platform, indicated that CNN, VGG16 and GoogleNet architectures yielded accuracies of 73.44%, 75.25% and 73.93%, respectively.
