Early Diabetic Retinopathy Research Articles

Asiatic acid attenuates diabetic retinopathy through TLR4/MyD88/NF-κB p65 mediated modulation of microglia polarization

AimThis study aimed to evaluate the effects of Asiatic acid (AA), a naturally occurring compound of pentacyclic triterpenoid, on the pathological processes of diabetic retinopathy (DR). MethodsSD rats were induced to develop early DR by intraperitoneal injection of STZ (60 mg/kg). Four weeks after injection, the diabetic rats were orally administrated with 37.5 mg/kg or 75 mg/kg AA every day for four weeks. The integrity of blood-retinal barrier (BRB) was measured by Evans blue staining. The polarization of microglia was determined by real-time PCR, western blot, and ELISA assays. The inner BRB (iBRB) or outer BRB (oBRB) breakdown was induced in human retinal endothelial cells or APRE19 cells through co-culture with high glucose and LPS-stimulated microglia BV2 cells. The damage to the iBRB and oBRB was measured using transendothelial/transepithelial electrical resistance (TEER/TER) and FITC-conjugated dextran cell permeability assays. Key findingsResults demonstrated that AA alleviated BRB breakdown, as evidenced by decreased protein expression of occludin, claudin-5, and ZO-1. Furthermore, AA treatment suppressed inflammation and M1 polarization, while it increased M2 polarization in the retina of DR rats. In vitro, the iBRB or oBRB breakdown was alleviated by AA. LPS-induced M1-polarization of BV2 cells under high glucose condition was also repressed through AA administration. Finally, we demonstrated that AA weakened the TLR4/MyD88/NF-κB p65 signaling pathway both in vivo and in vitro. SignificanceAA ameliorated early DR by regulating microglia polarization via the TLR4/MyD88/NF-κB p65 pathway. These data indicate that AA is a potential candidate for DR treatment.

Efficacy of pan retinal photocoagulation sub- threshold micropulse diode laser in diabetic retinopathy

Background: Diabetic retinopathy occurs as a complication of systemic diabetes . The potential use of laser for the treatment of severe non proliferative diabetic retinopathy (SNPDR) and early PDR provides another dimension in the management due to its long-term effects and relatively low costs. Objective: Evaluate the efficacy of sub threshold micro pulse diode laser in pan retinal photocoagulation for severe non proliferative and early proliferative diabetic retinopathy. Patients and methods: This prospective study included 40 eyes of 22 subjects with diabetic retinopathy in the period between November 2019 to December 2020. History taking and ophthalmological examination and Fundus Fluorescein Angiography (FFA) were performed on all patients prior to intervention. Diode laser (810 nm) panretinal photocoagulation was performed . Follow up was conducted at 3 visits at two weeks ,1and 3 months. During each of these visits the patient’s BCVA were measured and FFA was done after 3 months. Results: There was a statistically significant increase in the BCVA at 2 weeks that decreased again at 1 month and 3 months postoperative with no statistically significant difference . According to the stage of the disease; 28 eyes remain stable with final VA similar to their initial VA, 7 eyes showed improvement in their VA and 5 eyes showed deterioration of their VA. Conclusion: There was no evidence of laser effect or injury to the retinal pigment epithelium (RPE) or neurosensory retina. SDM may have a preventive role to delay progression of SNPDR and early PDR during the follow up period.

Plasma miR-26a-5p is a biomarker for retinal neurodegeneration of early diabetic retinopathy.

Retinal neurodegeneration is an early pathological change in diabetic retinopathy (DR). Early-stage retinal neurodegeneration is usually asymptomatic. This study aims to identify circulating microRNAs (miRNAs) as sensitive biomarkers for early retinal neurodegeneration. We profiled the plasma miRNA expression in three mild nonproliferative diabetic retinopathy (NPDR) cases and three matched non-DR patients using RNA sequencing. The differential miRNAs were validated with qRT-PCR. The retinal nerve fibre layer (RNFL) thickness of the eyes was measured using spectral-domain Optical coherence tomography (SD-OCT). The association between differential miRNAs and RNFL thickness was analysed using the Pearson correlation analysis. Bioinformatics tools were used to predict potential targets of miRNA associated with RNFL thickness and investigate the functions of the potential target genes. RNA sequencing identified 69 differential miRNAs and eight of them were reported to be associated with DR. The qRT-PCR for these eight miRNAs validated the down-regulation of circulating miR-26a-5p and miR-126-5p in a larger validating cohort. A positive correlation between plasma miR-26a-5p level and the RNFL thickness of the superior quadrant of both eyes was identified in another cohort, including 33 mild NPDR cases, 33 matched non-DR patients and 20 healthy controls. Furthermore, 367 candidate targets of miR-26a-5p were predicted. The functional studies revealed that these target genes are profoundly involved in various cellular functions and signalling pathways. Circulating miR-26a-5p is a potential biomarker for early-stage retinal neurodegeneration and it may be involved in the development of DR via profoundly influencing the functions of retinal cells.

Combination of pathological and spectroscopic characterization to promote diagnosis of retinal pigment epithelium-Bruch’s membrane complex in a diabetic rat model

Diabetic retinopathy (DR) is a common condition of diabetes, and approaches to detecting early DR using the unique characteristics of the retinal pigment epithelium-Bruch's membrane complex (RBC) have increasingly attracted attention. A diabetic model was established in Sprague-Dawley rats via streptozocin (STZ) injection for 1 (DM1) and 6 months (DM6), confirmed by weekly blood glucose measurement. Serum and retinal tissue-based advanced glycation endproducts (AGE) levels significantly elevated in diabetic rats, and RBC was evaluated by transmission electron microscopy and Raman spectroscopy. The results showed that whole Raman spectra and all marked band intensities could respectively achieve almost equal and accurate discrimination of all animal groups, along with the determination of important molecules from the band data. Further quantitative analyses indicated series of metabolic disturbance due to hyperglycemia were involved while the body self-regulation mechanism still played a role with different effects during the disease progression. Given this, Raman spectroscopy can reliably distinguish the early characterization of DR in addition to providing intrinsic key molecules that is sensitive to identify the early disease progression.

A Survey: Deep Learning Methods on Diabetic Retinopathy

Diabetes Mellitus (DM) is a metabolic condition that arises because of the elevated level of blood sugar in the body which triggers eye deficiency, also known as Diabetic Retinopathy (DR) which causes severe vision loss. An effective and efficient tool for early DR diagnosis and assisting experts is a computer-aided diagnosis (CAD) device focused on retinal fundus images that can detect this problem. A CAD method requires different phases in fundus images, such as identification, segmentation and lesion classification. Recent advancement of deep learning (DL) and its definitive victory over conventional ML approaches inspired researchers for implementation of many deep-learning-based techniques using different phases of fundus images. This paper highlights these deep learning approaches along with their pros and cons.

Decreased expression of TIPE2 in the eye under high-glucose conditions tested in vivo and in vitro

AimsInflammation is important in the development of angiogenesis diabetic retinopathy (DR). Anti-inflammation is promising strategy in early DR management. This study aimed to evaluate the level of tumour necrosis factor (TNF)-α-induced protein-8 like-2 (TIPE2), a formerly anti-inflammatory factor, under high-glucose conditions. MethodsTIPE2 was detected in the ① retina from db/db and streptozotocin-induced diabetic mice; ② vitreous fluid of patients with proliferative diabetic retinopathy (PDR) and ③ mouse retinal microendothelial cells (RMEC) cultured in glucose of varying concentrations. In situ expression was evaluated by immunohistochemistry and immunofluorescence assay. The expression of protein was analysed by Western blot or ELISA and mRNA by qRT-PCR. ResultsTIPE2 was down-regulated in the retina of the mice with diabetes. TIPE2 was present in the cytoplasm of RMEC and down-regulated in high-glucose conditions in line with concentration and time. The expression of TIPE2 in the vitreous fluid of patients with PDR was significantly lower than that without diabetes. Silencing TIPE2 by an siRNA resulted in increased expression of vascular endothelial growth factor (a vital factor in the development of DR), TNF-α and IL-1β. ConclusionsTIPE2 down-expressed and exerted anti-VEGF and anti-inflammatory function in the high-glucose environment. TIPE2 was verified to be involved in the process of DR and might be a potential regulator for DR development.

Association between risk factors and retinal nerve fiber layer loss in early stages of diabetic retinopathy.

To investigate the changes of retinal nerve fiber layer (RNFL) among normal individuals, diabetic patients without diabetic retinopathy (NDR) and non-proliferative diabetic retinopathy (NPDR), and explore the possible risk factors of early diabetic retinopathy (DR). In this cross-sectional study, 107 participants were divided in three groups. Totally 31 normal individuals (control group), 40 diabetic patients without DR (NDR group) and 36 patients with NPDR (NPDR group) were included. Optical coherence tomography (OCT) was used to detect RNFL thickness and other optic disc parameters among different groups. The potential association between RNFL loss and systemic risk factors were assessed for DR, including diabetes duration, body mass index (BMI), hemoglobin A1c (HbA1c), serum lipids, and blood pressure. The average and each quadrant RNFL thickness were thinner in NPDR group compared to control group of the right (P=0.00, P=0.01, P=0.01, P=0.02, P=0.04) and left eyes (P=0.00, P=0.00, P=0.00, P=0.03, P=0.04). The average, superior and inferior RNFL thickness were thinner in NDR group compared to the NPDR group of the right (P=0.00, P=0.02, P=0.03) and left eyes (P=0.00, P=0.00, P=0.01). Diabetic duration was negatively correlated with the superior, inferior, and average RNFL thickness of the right (r=-0.385, P=0.001; r=-0.366, P=0.001; r=-0.503, P=0.000) and left eyes (r=-0.271, P=0.018; r=0.278, P=0.015; r=-0.260, P=0.023). HbA1c was negatively correlated with the superior, inferior, and average RNFL thickness of the right (r=-0.316 P=0.005; r=-0.414, P=0.000; r=-0.418, P=0.000) and left eyes (r=-0.367, P=0.001; r=-0.250, P=0.030; r=-0.393, P=0.000). Systolic pressure was negatively correlated with the inferior and average RNFL thickness of the right eye (r=-0.402, P=0.000; r=-0.371, P=0.001) and was negatively correlated with the superior and average RNFL thickness of the left eye (r=-0.264, P=0.021; r=-0.233, P=0.043). RNFL loss, especially in the superior and inferior quadrants, may be the earliest structural change of the retina in diabetic patients, and is also associated with diabetic duration, HbA1c, and systolic pressure.

Exposure to Porphyromonas gingivalis and Modifiable Risk Factors Modulate Risk for Early Diabetic Retinopathy.

PurposeWe hypothesized that exposure to Porphyromonas gingivalis (Pg) increases the risk for early diabetic retinopathy (DR) and that the risk can be modulated.MethodsWe identified 116 early DR cases, and 116 non-DR controls were selected randomly by frequency matching for age, sex, race, and education from the US Third National Health and Nutrition Examination Survey. DR was assessed using non-mydriatic fundus photographs and graded by trained graders using the Modified Airlie House Classification scheme and the Early Treatment for Diabetic Retinopathy Study severity scale. Serum Pg immunoglobulin G (IgG) antibody (Ab) was measured in enzyme-linked immunosorbent assay units. Logistic regression was used to relate serum Pg IgG Ab levels to the risk for early DR.ResultsPer tenfold increase in Pg IgG Ab levels, there was an over 60% increased risk for early DR (odds ratio = 1.64; 95% confidence interval, 1.36–1.97), and a linear trend was noted for the estimated probabilities of early DR at various Pg IgG Ab levels (P for trend = 0.0053). The analysis also suggested that moderate alcohol consumption (less than 12 drinks in the past 12 months; P for interaction = 0.0003) and maintaining a normal serum glycated hemoglobulin level (HbA1c ≤ 5.7%; P for interaction < 0.0001) helped reduce the Pg-related DR risk.ConclusionsThe increased Pg-related DR risk could be alleviated by managing alcohol consumption and maintaining a normal blood glucose level.Translational RelevanceFindings from this study provide new directions for developing novel therapeutics and prevention strategies for DR.

Gypenoside XVII alleviates early diabetic retinopathy by regulating Müller cell apoptosis and autophagy in db/db mice

Diabetic retinopathy (DR) is a widespread vision-threatening disease in working people. Müller cells are important glial cells that participate in the blood retinal barrier and promote the maintenance of retinal physiological and structural homeostasis. Müller cell apoptosis and autophagy play an important role in the pathogenesis of DR. Gypenoside XVII (Gyp-17) exerts strong antiapoptotic and autophagic activities. However, the effect of Gyp-17 on DR and its mechanism of action have not been elucidated. This study explored the effect of Gyp-17 on early DR and Müller cell injury in db/db mice. Blood glucose and blood lipids were measured. Optical coherence tomography and fundus fluorescein angiography were applied to detect retinal thickness and vascular leakage, respectively. Hematoxylin eosin staining assessed the pathological changes of the retina. Retinal oxidative environment and cell apoptosis and autophagy were monitored using commercial kits, immunofluorescence, and Western blot assays. Results showed that Gyp-17 exerted no significant effect on blood glucose and lipid levels but maintained normal retinal permeability, physiological structure, high anti-oxidative enzyme expression, and the thickness of the inner nuclear layer compared with the model group. Moreover, Western blot analysis and TUNEL assay indicated that Gyp-17 significantly decreased pro-apoptotic-related protein expression and increased pro-autophagy-related protein expression compared with the model group. Immunofluorescence colocalization exhibited that the regulating action of Gyp-17 may focus on Müller cells. These data strongly demonstrate that Gyp-17 prevents early DR by decreasing apoptosis and increasing autophagy in Müller cells. Gyp-17 may be a candidate drug for early DR therapy.

Retinal microglia polarization in diabetic retinopathy.

Microglia, the main immune cell of the central nervous system (CNS), categorized into M1-like phenotype and M2-like phenotype, play important roles in phagocytosis, cell migration, antigen presentation, and cytokine production. As a part of CNS, retinal microglial cells (RMC) play an important role in retinal diseases. Diabetic retinopathy (DR) is one of the most common complications of diabetes. Recent studies have demonstrated that DR is not only a microvascular disease but also retinal neurodegeneration. RMC was regarded as a central role in neurodegeneration and neuroinflammation. Therefore, in this review, we will discuss RMC polarization and its possible regulatory factors in early DR, which will provide new targets and insights for early intervention of DR.

A Novel Approach of Diabetic Retinopathy Early Detection Based on Multifractal Geometry Analysis for OCTA Macular Images Using Support Vector Machine

Diabetic Retinopathy (DR) is a complication of diabetes that affects the eyes. It is caused by blood vessel damage of the light-sensitive tissue at the back of the retina. Neovascularization are emerged and the small blood vessels are blocked. The prevention or delaying vision loss can be obtained by DR early detection. The retinal microvascular network as a biological system has its own multifractal features as generalized dimensions, lacunarity and singularity spectrum. In this study, a novel approach for DR early detection based on the multifractal geometry has been proposed in some details. Analyzing the macular optical coherence tomography angiography (OCTA) images for diagnosing early non-proliferative diabetic retinopathy (NPDR). Using a supervised machine learning method as a Support Vector Machine (SVM) algorithm to automate the diagnosis process and improving the resultant accuracy. The classification technique had achieved 98.5 % accuracy. This approach also can classify easily other diabetic retinopathy stages or other retinal diseases, which affect the vessels or neovascularization distribution.

Fenofibrate Reduces the Severity of Neuroretinopathy in a Type 2 Model of Diabetes without Inducing Peroxisome Proliferator-Activated Receptor Alpha-Dependent Retinal Gene Expression.

Fenofibrate slows the progression of clinical diabetic retinopathy (DR), but its mechanism of action in the retina remains unclear. Fenofibrate is a known agonist of peroxisome proliferator-activated receptor alpha (PPARα), a transcription factor critical for regulating metabolism, inflammation and oxidative stress. Using a DR mouse model, db/db, we tested the hypothesis that fenofibrate slows early DR progression by activating PPARα in the retina. Relative to healthy littermates, six-month-old db/db mice exhibited elevated serum triglycerides and cholesterol, retinal gliosis, and electroretinography (ERG) changes including reduced b-wave amplitudes and delayed oscillatory potentials. These pathologic changes in the retina were improved by oral fenofibrate. However, fenofibrate did not induce PPARα target gene expression in whole retina or isolated Müller glia. The capacity of the retina to respond to PPARα was further tested by delivering the PPARα agonist GW590735 to the intraperitoneal or intravitreous space in mice carrying the peroxisome proliferator response element (PPRE)-luciferase reporter. We observed strong induction of the reporter in the liver, but no induction in the retina. In summary, fenofibrate treatment of db/db mice prevents the development of early DR but is not associated with induction of PPARα in the retina.

A Fuzzy clustering Approach for Micro Aneurysm Lesion Detection in Diabetic Retinopathy

Diabetic retinopathy (DR) be the significant difficulty of diabetes, and micro aneurysm (MA) is an earliest diabetic retinopathy lesion, making early detection of MA a key factor in diabetic retinopathy. DR is a direct or indirect effect on human vision caused by chronic diabetes. During its early stages DR is asymptomatic, and the late diagnosis leads to undeviating vision loss. The computer-assisted diagnosis helps with prompt and effective care, with the aid of medical photos. MA mark the beginning of DR making it a vital screening stage for this disorder. Diabetic retinopathy is a persistent infection of eye that can be the reason of blindness unless it is diagnosed and treated in due course. Early discovery with analysis of diabetic retinopathy is vital to vision preservation of patient. Precise recognition of MA be the crucial method towards early diagnosis of DR, since they occur as the first symptom of the disease. The segmentation of MA is performed using the Fuzzy C algorithm, and the extraction of features is performed with Gray Level Co-occurrence Matrix ( GLCM) as the set of characteristic for KNN. This technique aims to improve classification accuracy within an ensemble. A procedure is suggested here that recognizes the first DR sign called MA using images from the retinal fundus. Effective diagnosis of DR is very critical in the defense of patients' right to see. The procedure proposed is tested using publicly available databases of retinal images and greater accuracy is achieved.

Risk factors associated with retinopathy in young people with type 1 diabetes in Bangladesh.

ObjectivesDiabetic retinopathy (DR) is the most common microvascular complications seen in children and adolescents with type 1 diabetes. The aim of this study was to evaluate the prevalence of retinopathy and its association with other risk factors in young people with type 1 diabetes.MethodsThis study was a cross‐sectional study, which was done as part of the ongoing complication assessment in the paediatric diabetes clinic in BIRDEM (Bangladesh Institute of Research and Rehabilitation of Diabetes Endocrine and Metabolic Disorders), a tertiary care hospital. Children, adolescents and young adults with type 1 diabetes who were having diabetes duration >2 years were included in this study. Retinopathy was detected using fundal photography, and grading was done by National Screening Committee of UK by trained ophthalmologists.ResultsDiabetic retinopathy was observed in 44 (6.6%) patients. Majority (95.4%) of them had early diabetic retinopathy in the form of mild NPDR (nonproliferative diabetic retinopathy) (R1). Patients with retinopathy had higher HbA1c 9.6[8.4‐12.3] vs 9.1 [7.9‐10.8] (P = .013), longer duration of diabetes 7.6 [5.5‐10.7] vs 6.0 [4.5‐8.2] years (P = .001) and were older 21.5 [18.0‐23.0] vs 18 [16.0‐21.0] years (P = .0001) compared with those without retinopathy. On multivariate regression analysis, higher age and median HbA1c were significantly associated with DR.ConclusionsHigher HbA1c was the only modifiable risk factor for development of DR in our study population. Early detection of DR with improvement of glycaemic control may reduce the risk of progression of severe stages of the disease.

Interphotoreceptor Retinol-Binding Protein Ameliorates Diabetes-Induced Retinal Dysfunction and Neurodegeneration Through Rhodopsin.

Patients with diabetes often experience visual defects before any retinal pathologies are detected. The molecular mechanism for the visual defects in early diabetes has not been elucidated. Our previous study reported that in early diabetic retinopathy (DR), rhodopsin levels were reduced due to impaired 11-cis-retinal regeneration. Interphotoreceptor retinol-binding protein (IRBP) is a visual cycle protein and important for 11-cis-retinal generation. IRBP levels are decreased in the vitreous and retina of DR patients and animal models. To determine the role of IRBP downregulation in the visual defects in early DR, we induced diabetes in transgenic mice overexpressing IRBP in the retina. IRBP overexpression prevented diabetes-induced decline of retinal function. Furthermore, IRBP overexpression also prevented decreases of rhodopsin levels and 11-cis-retinal generation in diabetic mice. Diabetic IRBP transgenic mice also showed ameliorated retinal oxidative stress, inflammation, apoptosis, and retinal degeneration compared with diabetic wild-type mice. These findings suggest that diabetes-induced IRBP downregulation impairs the regeneration of 11-cis-retinal and rhodopsin, leading to retinal dysfunction in early DR. Furthermore, increased 11-cis-retinal–free opsin constitutively activates the phototransduction pathway, leading to increased oxidative stress and retinal neurodegeneration. Therefore, restored IRBP expression in the diabetic retina may confer a protective effect against retinal degeneration in DR.

An IoT-Cloud Based Intelligent Computer-aided Diagnosis of Diabetic Retinopathy Stage Classification Using Deep Learning Approach

Diabetic retinopathy (DR) is a disease with an increasing prevalence and the major reason for blindness among working-age population. The possibility of severe vision loss can be extensively reduced by timely diagnosis and treatment. An automated screening for DR has been identified as an effective method for early DR detection, which can decrease the workload associated to manual grading as well as save diagnosis costs and time. Several studies have been carried out to develop automated detection and classification models for DR. This paper presents a new IoT and cloud-based deep learning for healthcare diagnosis of Diabetic Retinopathy (DR). The proposed model incorporates different processes namely data collection, preprocessing, segmentation, feature extraction and classification. At first, the IoT-based data collection process takes place where the patient wears a head mounted camera to capture the retinal fundus image and send to cloud server. Then, the contrast level of the input DR image gets increased in the preprocessing stage using Contrast Limited Adaptive Histogram Equalization (CLAHE) model. Next, the preprocessed image is segmented using Adaptive Spatial Kernel distance measure-based Fuzzy C-Means clustering (ASKFCM) model. Afterwards, deep Convolution Neural Network (CNN) based Inception v4 model is applied as a feature extractor and the resulting feature vectors undergo classification in line with the Gaussian Naive Bayes (GNB) model. The proposed model was tested using a benchmark DR MESSIDOR image dataset and the obtained results showcased superior performance of the proposed model over other such models compared in the study.

Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier

Abstract Objectives The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels. Methods The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the tri-DWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Rate-based Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy. Results The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB. Conclusions The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.

WITHDRAWN: Detection of diabetic retinopathy using partial swarm optimization (PSO) and Gaussian interval type-2 fuzzy membership functions (GIT2FMFS)

Abstract Vision loss due to Diabetic Retinopathy (DR) is an important cause of disability in the population since it affects 3.4 percent of the population. To avoid this problem, we have to detect DR as in early stage. In early stage DR is symptomless; screening is the only way to detect and classify these kinds of diseases. Several automated screening techniques are used to detect DR in retina. Still it took more time. So, our proposed work introduces image processing based soft computing approaches. It will improve the performance of accuracy, sensitivity, specificity and precision and detect the DR in easier and faster manner. This paper presents a novel approach for detection of microaneurysms and Hemorrhages in fundus images. Our process includes following steps i) Pre-Processing ii) Blood Vessel Segmentation iii) Blood Vessel Removal iv) Fovea Localization v) Fovea Elimination vi) Feature Extraction vii) Feature Selection and finally viii) Detection of Diabetic Retinopathy disease such as microaneurysms and hemorrhages. Our experimental results based on MATLAB simulation tool and it take databases of DR2 and MESSIDOR. These databases provide efficient and effective results in classification method.

A New Early Stage Diabetic Retinopathy Diagnosis Model Using Deep Convolutional Neural Networks and Principal Component Analysis

Diabetic retinopathy (DR) is a disease of the retina, which leads over time to vision problems such retinal detachment, vitreous hemorrhage, glaucoma, and in worse cases leads to blindness, which can initially be controlled by periodic DR-screening. Early diagnosis will lead to greater control of the disease, whereas performing retinal examinations on all diabetic patients is an unattainable need, as diabetes is a chronic disease and its global prevalence has been steadily increasing over the past few decades. According to recent World Health Organization statistics, about 422 million people worldwide have diabetes, the majority living in low-and middle-income countries. This paper proposes a new strategy that brings the strength of convolutional neural networks (CNNs) to the diagnosis of DR. Coupled with using principal component analysis (PCA) that performs dimension reduction to improve the diagnostic accuracy, the proposed model exploiting edge-preserving guided image filtering (E-GIF) that performs as a contrast enhancement mechanism, and in addition to smoothing low gradient areas, it also accentuates strong edges. Diabetic retinopathy causes progressive damage to the blood vessels in the retina to the extent that it leaves traces and lesions in the tissues of the retina. These lesions appear in the form of edges and when processing retinal images, we seek to accentuate these edges to enable better diagnosis of diabetic retinopathy symptoms. A new CNN architecture with residual connections is used, which performs very well in diagnosing DR. The proposed model is named with RUnet-PCA: Residual U-net Deep CNN with Principal Component Analysis. The well-known AlexNet, VggNet-s, VggNet-16, VggNet-19, GoogleNet, and ResNet models were adopted for comparison with the proposed model. Publicly available Kaggle dataset was employed for training exploring the DR diagnosis accuracy. Experimental results show that the proposed RUnet-PCA model achieved a diagnosis accuracy of 98.44% and it was extremely robust and promising in comparison to other diagnosis methods.

Early Diabetic Nephropathy and Retinopathy in Patients with Type 1 Diabetes Mellitus Attending Sudan Childhood Diabetes Centre.

Objective Data on microvascular complications in children and adolescents with type 1 diabetes mellitus (T1DM) in Sudan are scarce. This study was aimed at determining the prevalence of diabetic nephropathy (DN) and retinopathy (DR) and their relationship to certain risk factors in children with T1DM attending the Sudan Childhood Diabetes Centre. Design and Methods. A clinic-based cross-sectional study of 100 patients with T1DM aged 10-18 years. Patients with disease duration exceeding 5 years if the onset of diabetes was prepubertal and 2 years if it was postpubertal were included. Relevant sociodemographic, clinical, and biochemical information was obtained. Blood pressure was measured. The patients were screened for DN and DR using urinary microalbumin estimation and fundus photography, respectively. Results The frequency of microalbuminuria and diabetic retinopathy was 36% and 33%, respectively. Eleven percent had both retinopathy and microalbuminuria. Seven percent of the patients were found to be hypertensive. Patients with diabetic retinopathy had significantly higher HbA1c levels (p = 0.009) and longer diabetes duration (p = 0.02) than patients without retinopathy. Logistic regression showed that high HbA1c (odds ratio (OR) 0.83, confidence interval (CI) 0.68-1.00, p = 0.04), but not age, duration, ethnic group, BMI, blood pressure, and presence of nephropathy, was an independent risk factor for retinopathy. Likewise, high blood pressure (OR 6.89, CI 1.17-40.52, p = 0.03), but not age, duration, ethnic group, BMI, HbA1c, and presence of retinopathy, was a predictor for nephropathy. Conclusion High prevalence of incipient DN and early stages of DR were observed in this study. Longer diabetes duration and higher HbA1c were associated with the presence of diabetic retinopathy. High blood pressure was a risk factor for DN. So regular screening for these complications and optimization of glycemic control are needed.