Search

Diabetic Retinopathy is a diabetic disease that directly affects the vision that causes damaged blood vessels at the back end of the eyes. It a complicated disease that cannot be recognized from normal eyes; a fundus imaging can reflect the impairments over the retina that causes partial or complete blindness that cannot be cured. It is mandatory for a routine examination that may lead to prevent from complete blindness because it can be prevented from current damaged blood vessels but it cannot be revert or treated. In the field of image processing; various diseases can be diagnosed automatically that saves humans life along with easiness for medical professionals. If a person pertains diabetes for a long time may have highest possibility for diabetic retinopathy. Here, the system has been proposed that can diagnose this disease with high level of accuracy with minimal false alarm rate. System uses Prewitt Edge Detection and Color Mapping techniques for recognizing diabetic retinopathy symptoms or damaged blood vessels from fundus imaging. Prewitt is highly sensitive for extracting impairments along with blood vessels and system is able to mask the unwanted area by using color correction tool.

Purposes: To describe the development and validation of an artificial intelligence-based, deep learning algorithm (DeepDR) for the detection of diabetic retinopathy (DR) in retinal fundus photographs. Methods: Five hundred fundus images, which had detailed labelling of DR lesions, were transmitted to be analysed, including localization of the optic disk and macular, vessel segmentation, detection of lesions, and grading of DR. The multi-level iterative method of convolutional neural network and the strategy of enhanced learning were used to improve the accuracy of the system (DeepDR) for grading DR. Three public data sets were used to further train the software. The final grading results were tested based on the fundus images provided by the hospitals. Results: For 6788 fundus images (both macular and disc centred) of two Hospital Eye Center, the detection of microaneurysm, haemorrhage and hard exudates had an accuracy of 99.7%, 98.4% and 98.1%, respectively. The current algorithm accuracy was 0.96. Another 20,000 fundus images from community screening were selected, and 7593 photos of poor quality were excluded according to quality standards. Accuracy for accurate staging of fundus photos: accuracy was 0.9179. The sensitivity, specificity and area under the curve (AUC) were 80.58%, 95.77% and 0.9327, respectively. Conclusions: This artificial intelligence-based DeepDR can be used with high accuracy for the detection of DR in retinal images. This technology offers the potential to increase the efficiency and accessibility of DR screening programs.

Diabetes Mellitus or Diabetes occurs when the glucose content in blood is high. Diabetes Mellitus affects the eye. Diabetes Mellitus leads to the damage of blood vessels of retina termed as Diabetic Retinopathy. Diabetic Retinopathy in its initial stage has no /mild symptoms. But the progression rate of Diabetic Retinopathy is very high. Eventually, Diabetic Retinopathy causes unexpected visualization failure left untreated. Computer Aided Diagnosis (CAD) systems assist doctors during diagnosis. This paper proposes an automatic diagnosis system to accurately classify the stages of Diabetic Retinopathy in Optical Coherence Tomography retinal images using Convolutional Neural Networks.

Aim To develop an automatic tool on screening diabetic retinopathy (DR) from diabetic patients. Methods We extracted textures from eye fundus images of each diabetes subject using grey level co-occurrence matrix method and trained a Bayesian model based on these textures. The receiver operating characteristic (ROC) curve was used to estimate the sensitivity and specificity of the Bayesian model. Results A total of 1000 eyes fundus images from diabetic patients in which 298 eyes were diagnosed as DR by two ophthalmologists. The Bayesian model was trained using four extracted textures including contrast, entropy, angular second moment and correlation using a training dataset. The Bayesian model achieved a sensitivity of 0.949 and a specificity of 0.928 in the validation dataset. The area under the ROC curve was 0.938, and the 10-fold cross validation method showed that the average accuracy rate is 93.5%. Conclusion Textures extracted by grey level co-occurrence can be useful information for DR diagnosis, and a trained Bayesian model based on these textures can be an effective tool for DR screening among diabetic patients.

It is desirable to diagnose diabetic retinopathy at an early stage for developing a suitable treatment plan to prevent the condition from deteriorating. To provide an immediate diagnosis of the retina, various methods have been investigated to realize a time and cost effective classification of the fundus images. However, most diabetic retinopathy automated identification methods are structural based analysis. Moreover, Asian fundus images have larger optic disc and thicker retinal vessels compared with Caucasians. Hence, we explore a machine learning approach to the extraction of texture features for classification and the feasibility of this approach using texture parameters to complement current algorithms. Normal retina, non-proliferative diabetic retinopathy and proliferative diabetic retinopathy are identified in this paper. The first step is achieved with three groups of texture features such as gray level co-occurrence matric texture features, different statistical features and run length matrix texture features extracted. In the second step, these features are fed into an optimized random forest classifier for automatic classification. We test our system on two databases (D1 and D2) consisting of 432 and 579 fundus images from a diabetic retinopathy screening program consisting of Asians. The diabetic retinopathy is successfully diagnosed with sensitivity is 0.936 ± 0.019 for D1 and 0.941 ± 0.016 for D2, specificity is 0.917 ± 0.011 for D1 and 0.918 ± 0.011 for D2, positive predictive value is 0.924 ± 0.013 for D1 and 0.939 ± 0.012 for D2, when training on the same institutions, respectively.

One of the causes of blindness among working-age adults is the diabetic retinopathy (DR). The DR raise the damage of the retina if it is not early diagnosed and treated. In the present paper, we are focusing on the detection of the primary signs of the diabetic retinopathy which is the exudate. The exudate appeared in white or yellow color with different shapes, sizes and positions. More its position is close to the optic disk, more the percentage of blindness is increased. That's why the position and the size are two important information for an ophthalmologist to distinguish or diagnose the severity of the disease. For those reasons, we aim in this paper to detect and segment the exudate using Random Forest classifier. A DR database used with the application of a Random Forest classifier to segment these regions. The impact of varying the main parameter of the random forest algorithm is studied. We achieved the highest value of the specificity and the accuracy with 99.5% and 99.50% respectively. An area under curve (AUC) of 0.952 is obtained.

PURPOSE We assessed the suitability of a low-cost, handheld, nonmydriatic retinograph, namely the Horus DEC 200, for diabetic retinopathy (DR) diagnosis. Two factors were considered: ease of image acquisition and image quality. METHODS One operator acquired fundus photographs from 54 patients using the Horus and AFC-330, a more expensive, nonportable retinograph. Satisfaction surveys were filled out by patients. Then, two retinologists subjectively assessed image quality and graded DR severity in one eye of each patient. Objective image quality indices also were computed. RESULTS During image acquisitions, patients had difficulty locating the fixation target inside the Horus: by default, 53.7% of them had to fixate external points with the contralateral eye, as opposed to none of them using the AFC-330 (P < 0.0001). This issue impacted the duration of image acquisitions. Images obtained by the Horus were of significantly lower quality according to the experts (P = 0.0002 and P = 0.0004) and to the objective criterion (P < 0.0001). As a result, up to 20.4% of eyes were inadequate for interpretation, as opposed to 9.3% using the AFC-330. However, no significant difference was found in terms of DR severity according to both experts (P = 0.557 and P = 0.156). CONCLUSIONS The Horus can be used to screen DR, but at the cost of longer examination times and higher proportions of patients referred to an ophthalmologist due to inadequate image quality. TRANSLATIONAL RELEVANCE The Horus is adequate to screen DR, for instance in primary care centers or in mobile imaging units.

Diabetes affects the microangiopathy in the retina which causes to retinal disorders such as blood vessel blockage then the abnormal blood vessel is occurred. The microvascular leakage will decrease or loss of sight. The aim of this research is to find the retinal blood vessel detection method for diagnosis of diabetic retinopathy. This study was carried out using the principle of image processing to analyze the retina image. The green channel was used for data processing. Consequently, several image processing techniques were applied to the green channel data as image enhancement, scaling, morphological operator and filter to extract the features of the retinal blood vessel in the retina image. The retinal blood vessel was extracted and displayed on the screen for diagnosis. The efficiency of algorithm for the retinal blood vessel detection was presented in this study. All different twenty retinal images from the DRIVE database were tested for blood vessel extraction. The error detection data was compared with the ground truth image. The results show that the maximum specificity and accuracy were 99.66% and 96.80%, respectively. It indicated that the proposed method could detect the blood vessel from retina image.

Diabetic retinopathy (DR) leads to irreversible vision loss. Diagnosis and staging of DR is usually based on the presence, number, location and type of retinal lesions. Ultra-wide field (UWF) digital scanning laser technology provides an opportunity for computer-aided DR lesion detection. High-resolution UWF images (3078×2702 pixels) may allow detection of more clinically relevant retinopathy in comparison with conventional retinal images as UWF imaging covers a 200° retinal area, versus 45° by conventional cameras. Current approaches to DR diagnosis that analyze 7-field Early Treatment Diabetic Retinopathy Study (ETDRS) retinal images provide similar results to UWF imaging. However, in 40% of cases, more retinopathy was found outside the 7- field ETDRS fields by UWF and in 10% of cases, retinopathy was reclassified as more severe. The reason is that UWF images examine both the central retina and more peripheral regions. We propose an algorithm for automatic detection and classification of DR lesions such as cotton wool spots, exudates, microaneurysms and haemorrhages in UWF images. The algorithm uses convolutional neural network (CNN) as a feature extractor and classifies the feature vectors extracted from colour-composite UWF images using a support vector machine (SVM). The main contribution includes detection of four types of DR lesions in the peripheral retina for diagnostic purposes. The evaluation dataset contains 146 UWF images. The proposed method for detection of DR lesion subtypes in UWF images using two scenarios for transfer learning achieved AUC ≈ 80%. Data was split at the patient level to validate the proposed algorithm.

This paper aims to find an efficient hybrid method to diagnose diabetic retinopathy, which is an anomaly in the human eyes that occur due to the decrease of insulin content in the blood. Damages to the blood vessels in the light-sensitive tissue of the eye is its root cause. The symptoms of diabetic retinopathy are hemorrhages, exudates and micro-aneurysms. Eventually it will lead to total blindness. This erratic disorder is developed in people having both type-1 and type-2 diabetes. The longer period of time you have uncontrolled blood sugar levels, it is more likely that this condition of diabetic retinopathy may arise. Since the number of diabetic retinopathy patients are high in number, the significance of automating the diagnostic process is much more relevant. In order to diagnose this disease automatically, a hybrid and efficient system has been developed to interpret and analyse the 2D fundus images. Grayscale conversion and Contrast Level Adaptive Histogram Enhancement (CLAHE) has been performed as a pre-processing step to improve the quality of the input image which will further aid in blood vessel extraction and exudates determination in a better way. The pre-processed image is further manipulated with the Kirsch’s template for the blood vessel extraction. Subsequently, the features of the images are extracted from the morphologically processed images through a multi-level Maximally Stable Extremal Regions (MSER) to precisely extract and identify the exudates from the eye. The determination of exudates helps the ophthalmologist to diagnose the diabetic retinopathy and further proceed with respective treatment.

Diabetic retinopathy (DR) is a leading cause of vision loss in diabetic patients. DR is mainly caused due to the damage of retinal blood vessels in the diabetic patients. It is essential to detect and segment the retinal blood vessels for DR detection and diagnosis, which prevents earlier vision loss in diabetic patients. The computer aided automatic detection and segmentation of blood vessels through the elimination of optic disc (OD) region in retina are proposed in this paper. The OD region is segmented using anisotropic diffusion filter and subsequentially the retinal blood vessels are detected using mathematical binary morphological operations. The proposed methodology is tested on two different publicly available datasets and achieved 93.99% sensitivity, 98.37% specificity, 98.08% accuracy in DRIVE dataset and 93.6% sensitivity, 98.96% specificity, and 95.94% accuracy in STARE dataset, respectively.

purpose. To describe and evaluate a machine learning-based, automated system to detect exudates and cotton-wool spots in digital color fundus photographs and differentiate them from drusen, for early diagnosis of diabetic retinopathy. methods. Three hundred retinal images from one eye of 300 patients with diabetes were selected from a diabetic retinopathy telediagnosis database (nonmydriatic camera, two-field photography): 100 with previously diagnosed bright lesions and 200 without. A machine learning computer program was developed that can identify and differentiate among drusen, (hard) exudates, and cotton-wool spots. A human expert standard for the 300 images was obtained by consensus annotation by two retinal specialists. Sensitivities and specificities of the annotations on the 300 images by the automated system and a third retinal specialist were determined. results. The system achieved an area under the receiver operating characteristic (ROC) curve of 0.95 and sensitivity/specificity pairs of 0.95/0.88 for the detection of bright lesions of any type, and 0.95/0.86, 0.70/0.93, and 0.77/0.88 for the detection of exudates, cotton-wool spots, and drusen, respectively. The third retinal specialist achieved pairs of 0.95/0.74 for bright lesions and 0.90/0.98, 0.87/0.98, and 0.92/0.79 per lesion type. conclusions. A machine learning-based, automated system capable of detecting exudates and cotton-wool spots and differentiating them from drusen in color images obtained in community based diabetic patients has been developed and approaches the performance level of retinal experts. If the machine learning can be improved with additional training data sets, it may be useful for detecting clinically important bright lesions, enhancing early diagnosis, and reducing visual loss in patients with diabetes.

BACKGROUND: The Kilimanjaro Diabetic Programme used the Intervention Mapping framework to develop a theory- and evidence-based diabetic retinopathy screening programme. A Working Committee of health care workers and stakeholders ensured community engagement and empowerment of the target audience.OBJECTIVES: To deliver a culturally appropriate, sustainable, community supported health intervention, promoting eye health behaviour change, to prevent avoidable blindness.METHODS: The six steps of the Intervention Mapping protocol incorporated eight components: (1) a needs assessment of people with diabetes and health care workers (2) a clinical trial of diabetic retinopathy screening modes, (3) comic strips as a motivational strategy for diabetic retinopathy screening uptake, (4) health care worker education (5) an electronic database of people with diabetes (6) a self-carry diary (7) implementation of mobile diabetic retinopathy retinal screening (8) process and outcome programme evaluation.RESULTS: The programme eliminated barriers to diabetic retinopathy screening in Kilimanjaro Christian Medical Centre eye and diabetic clinics, placing a digital retinal screening camera in the diabetic clinic and a fast-track screening system in the eye clinic. Two comic strips and a diary provided information about self-management and record of medications, treatment, blood sugar and blood pressure at clinic visits. An annual rural health care worker education programme met requests for knowledge on treatment and care of diabetes, targeting prevention of diabetic retinopathy. Rural digital retinal screening was implemented. Rural diabetes clinics were initiated.CONCLUSIONS: Intervention Mapping provided a systematic, iterative model to formulate and deliver an urban and rural diabetic retinopathy screening programme.TRIAL REGISTRATION NUMBER: ISRCTN31439939. Details available at https://www.isrctn.com/.

INTRODUCTION: Intervention Mapping is the protocol used by the Kilimanjaro Diabetic Programme to plan, develop, implement, and evaluate an evidence-based screening programme for diabetic retinopathy. Two comic strips were developed to deliver the message on the need for diabetic retinopathy screening.OBJECTIVES: The first objective was to develop a culturally appropriate and accessible health message to promote diabetic retinopathy screening for the target audience. The second objective was to deliver a motivational message to promote acceptance of diabetic retinopathy screening irrespective of past eye health behaviour.METHODS: A multi-method research design was used. Social cognitive theory provided the theoretical basis for the intervention, involving community participation to promote positive eye health behaviour.RESULTS: For the Draughts Comic Strip, Flesch-Kincaid readability was 75.7% and comprehension was 87.04%, and for the Soap Opera Comic Strip Flesch-Kincaid readability was 75.6% and comprehension was 86.54%.CONCLUSION: The development of the diabetic retinopathy comic strips was a positive health education strategy implemented during a clinical trial comparing methods of screening for diabetic retinopathy at the Kilimanjaro Christian Medical Centre Hospital. The level of comprehension of the comic strips by stakeholders indicated their understanding of the message. Patients enroled in the clinical trial requested the comic strips. No discarded comic strips were found in the clinic during the clinical trial.TRIAL REGISTRATION: Trial registration number: ISRCTN31439939. Details available at https://www.isrctn.com/ .

Purpose: Diabetes mellitus is a leading cause of impaired vision. The objective of this study was to evaluate the feasibility of use of portable retinograph and remote analysis of images along with a virtual questionnaire for screening for diabetic retinopathy in basic health units in the city of Ribeirão Preto/SP during the Covid-19 pandemic. Methods: Standard Covid-19 protocol was followed during the screening. Blood pressure and capillary blood glucose were measured. Demographic and social data were collected through a standardized online questionnaire via smartphone. After pupillary dilation, fundal images were obtained with portable retinographs by trained ophthalmology residents. Two standardized 45° images were acquired: one posterior segment and another nasal to the optic nerve. Diabetic retinopathy was classified according to the Early Treatment Diabetic Retinopathy Study. Results: A total of 350 patients (64% female; 45% aged 55-70 years; 55% Caucasian) were evaluated. For 40.5% of patients, the campaign was the first opportunity for retinal evaluation; 47.56% had diabetes mellitus for >10 years. On repeat analysis of images stored in a cloud-based repository by retinal specialist, a 7.8% difference was observed in the Early Treatment Diabetic Retinopathy Study diabetic retinopathy classification, compared to the screening findings. Mild diabetic retinopathy was observed in 12.23%, moderate diabetic retinopathy in 6.31%, and proliferative diabetic retinopathy in 2.58% patients. Macular edema was present in 4.58% patients. Diabetic retinopathy was not detected in 72.78% patients. Conclusion: Use of portable retinographs together with telemedicine can provide efficient alternative to traditional methods for screening and diagnosis of diabetic retinopathy.

Purpose: To evaluate the diagnostic accuracy of a diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3. Methods: In this cross-sectional study, 295 fundus images were analysed by the CNN model and compared to a panel of ophthalmologists. Images were obtained from a dataset acquired within a screening programme. Diagnostic accuracy measures and respective 95% CI were calculated. Results: The sensitivity and specificity of the CNN model in diagnosing referable DR was 81% (95% CI 66–90%) and 97% (95% CI 95–99%), respectively. Positive predictive value was 86% (95% CI 72–94%) and negative predictive value 96% (95% CI 93–98%). The positive likelihood ratio was 33 (95% CI 15–75) and the negative was 0.20 (95% CI 0.11–0.35). Its clinical impact is demonstrated by the change observed in the pre-test probability of referable DR (assuming a prevalence of 16%) to a post-test probability for a positive test result of 86% and for a negative test result of 4%. Conclusion: A CNN model negative test result safely excludes DR, and its use may significantly reduce the burden of ophthalmologists at reading centres.

Aims To evaluate the timing and spectral-domain optical coherence tomography (SD-OCT) features of diabetic macular oedema (DME) recurrence according to baseline OCT patterns in patients treated with dexamethasone implant (DEX-I). Methods This is a retrospective observational study (72 eyes/65 patients). Best-corrected visual acuity, timing of DME recurrence, and SD-OCT pattern [intraretinal cysts (IRC), IRC plus subretinal fluid (mixed), external limiting membrane (ELM), ellipsoid (IS/OS) layer integrity] were assessed at baseline and monthly until first DME recurrence. Results Forty-two (58.3%) and 30 (41.6%) DME eyes had an IRC and mixed DME pattern at baseline, respectively. Twenty-four out of thirty mixed eyes (80%) relapsed without subretinal fluid. At baseline, mixed eyes showed similar changes in ELM and IS/OS (60 and 76.6% of eyes, respectively) versus IRC eyes (42.8 and 80.9% of eyes). After DME recurrence, more mixed eyes at baseline showed ELM and IS/OS changes (63.3 and 86.6%) than IRC eyes (50 and 76.2%). 33.3% of mixed eyes had DME recurrence at ≥ 6 months from first DEX-I implant versus 19% of IRC eyes. Conclusions Mixed DME eyes were treated with DEX-I relapse later and more frequently without subretinal fluid than IRC eyes. SD-OCT characteristics of different DME patterns at baseline can predict morphological features and timing of DME recurrence.

PURPOSE: We aimed to investigate changes in retinal vascular geometry over time after panretinal photocoagulation (PRP) in patients with proliferative diabetic retinopathy (PDR).METHODS: Thirty-seven eyes with PDR were included. Wide-field fluorescein angiography (Optomap, Optos PLC., Dunfermline, Scotland, UK) was used to diagnose PDR at baseline and to assess activity at follow-up month three and six. At each time-point, a trained grader measured retinal vessel geometry on optic disc (OD) centred images using semiautomated software (SIVA, Singapore I Vessel Assessment, National University of Singapore, Singapore) according to a standardized protocol.RESULTS: At baseline, the mean age and duration of diabetes were 52.8 and 22.3 years, and 65% were male. Mean HbA1c was 69.9 mmol/mol, and blood pressure was 155/84 mmHg. Of the 37 eyes with PDR, eight (22%) eyes had progression at month three and 13 (35%) progressed over six months. Baseline characteristics, including age, sex, duration of diabetes, HbA1c, blood pressure, vessel geometric variables and total amount of laser energy delivered did not differ by progression status. However, compared to patients with progression of PDR, patients with favourable treatment outcome had alterations in the retinal arteriolar structures from baseline to month six (calibre, 154.3 μm versus 159.5 μm, p = 0.04, tortuosity 1.12 versus 1.10, p = 0.04) and in venular structures from baseline to month three (fractal dimension 1.490 versus 1.499, p = 0.04, branching coefficient (BC) 1.32 versus 1.37, p = 0.01).CONCLUSION: In patients with PDR, successful PRP leads to alterations in the retinal vascular structure. However, baseline retinal vascular geometry characteristics did not predict treatment outcome.

Objective To determine alterations in retinal pigment epithelium (RPE), photoreceptor inner segment ellipsoid layer (ISel), and external limiting membrane (ELM) reflectivities using optical coherence tomography (OCT) image analysis in patients with mild nonproliferative diabetic retinopathy (NPDR). Design Retrospective, single-centre, controlled clinical study. Participants The study cohort included 42 eyes of 42 patients with mild NPDR (NPDR group) and 40 eyes of 40 healthy subjects (control group). Eyes with moderate and severe NPDR, proliferative DR, macular edema, and other macular pathologies were excluded. Methods The reflectivities of RPE, ISel, and ELM were calculated using a medical image-processing software based on greyscale OCT images. The differences in the reflectivity values between the NPDR and control groups were analyzed. Results The NPDR group comprised 22 males and 20 females (with a mean age of 61.3 ± 6.5 years), and the control group consisted of 14 males and 26 females (with a mean age of 63.0 ± 4.1 years) (p > 0.05). The ISel had significantly lower reflectivity (both absolute and relative) in eyes with mild NPDR compared with that of the control eyes (p < 0.001), whereas the reflectivities of RPE and ELM did not differ between the 2 groups (p = 0.126, p = 0.053 respectively). Conclusions Although previous ex vivo studies reported photoreceptor degeneration in diabetic retinopathy, this is the first clinical study to investigate retinal layer reflectivities in NPDR using OCT. In eyes with mild NPDR, ISel seems to have lower reflectivity, and this finding might indicate early photoreceptor degeneration in diabetic retinopathy pathogenesis. © 2015 Canadian Ophthalmological Society.