Diabetic Retinopathy Severity Grading Research Articles

Diabetic retinopathy detection using Bilayered Neural Network classification model with resubstitution validation

In recent years, eye diseases in diabetic patients are one of the most common has been diabetic retinopathy (DR). which leads to complete blindness in advanced stages. Diabetes affects the blood vessels in the retina and causes vision loss. One of the ways to decrease the risk of this issue is to detect diabetic retinopathy in its early stages. This study describes a computer-aided screening system (DREAM) that uses a neural network classification model in machine learning to assess fundus images with different illumination and fields of vision and provide a severity grade for diabetic retinopathy. Moreover, the methodology of this study based on:•Enhancement techniques have been used on dataset images, histogram equalization, noise reduction and image scaling,•vSLAM has been selected as feature extraction,•Bilayered Neural Network under resubstitution validation used as a classification model.Finally, after testing on the DR severity grading system is tested on 6332 images of detection of diabetic retinopathy images, the result of the ROC curve is 0.985 on image dataset and obtains accuracy reached 98.5%. The classification result has been founded under MATLAB platform, beside it that be work with real time analysis and detection when patient eyes analysis.

An enumerative pre-processing approach for retinopathy severity grading using an interpretable classifier: a comparative study.

Diabetic retinopathy (DR) is a serious eye complication that results in permanent vision damage. As the number of patients suffering from DR increases, so does the delay in treatment for DR diagnosis. To bridge this gap, an efficient DR screening system that assists clinicians is required. Although many artificial intelligence (AI) screening systems have been deployed in recent years, accuracy remains a metric that can be improved. An enumerative pre-processing approach is implemented in the deep learning model to attain better accuracies for DR severity grading. The proposed approach is compared with various pre-trained models, and the necessary performance metrics were tabulated. This paper also presents the comparative analysis of various optimization algorithms that are utilized in the deep network model, and the results were outlined. The experimental results are carried out on the MESSIDOR dataset to assess the performance. The experimental results show that an enumerative pipeline combination K1-K2-K3-DFNN-LOA shows better results when compared with other combinations. When compared with various optimization algorithms and pre-trained models, the proposed model has better performance with maximum accuracy, precision, recall, F1 score, and macro-averaged metric of 97.60%, 94.60%, 98.40%, 94.60%, and 0.97, respectively. This study focussed on developing and implementing a DR screening system on color fundus photographs. This artificial intelligence-based system offers the possibility to enhance the efficacy and approachability of DR diagnosis.

Effect of a self-care promoting program on engagement in self-care behaviors and health-related outcomes among persons with type 2 diabetes and diabetic retinopathy: A single-blind randomized controlled trial.

Diabetic retinopathy (DR) is the most common microvascular complication of diabetes, leading to visual impairment and eventual blindness. Promoting self-care behaviors is crucial in controlling DR progression and preventing blindness. This study aimed to investigate the effects of a Self-Care Promoting Program (SCPP) on engagement in self-care behaviors, HbA1c levels, visual acuity (VA), severity of DR, and vision-related quality of life (VRQoL) among individuals with type 2 diabetes and DR. This study employed a single-blind randomized controlled trial design to compare SCPP with conventional diabetic care interventions (standard care). The SCPP was based on the Self-Care of Chronic Illness Theory, Self-efficacy theory, and the Association of Diabetic Care and Education Specialist (ADCES) guidelines incorporating health education, self-care maintenance, monitoring, and management skills training over 12 weeks. Ninety-eight participants were randomly allocated to the experimental or control group (n = 49 per group). While the experimental group received SCPP alongside standard care, the control group received standard care alone. Data collection occurred between May 2022 and March 2023 and included demographic information, the Self-Care of Diabetes Index questionnaire (SCODI), the self-care for diabetes eye care questionnaire (SCFDE), the impact of visual impairment questionnaire (IVI-Thai version), and retinal images for DR severity grading. Data analysis utilized descriptive statistics, Chi-Square tests, t-tests, and MANOVA. Following 8 and 16 weeks of SCPP, the experimental group had significantly higher mean scores in engagement with self-care and eye-care behaviors compared to the control group (p <0.001). The highest scores were observed in self-care and eye-care confidence behaviors, followed by maintenance, monitoring, and management. Furthermore, HbA1c levels and VRQoL significantly decreased and were lower than those of the control group at week 16 (p <0.001 and p <0.05, respectively). However, there were no significant differences in VA, and DR severity increased in both groups by week 16. SCPP benefits individuals with DR, enhancing their confidence and ability to perform, monitor, and manage self-care behaviors. These strategies contribute to improved diabetes management, enhanced quality of life, and reduced DR-related blindness. Integrating SCPP into routine DR management is recommended, with nurses playing a pivotal role in overseeing and driving this integration, highlighting the critical role of nurses in managing this widespread global disease. Thai Clinical Trials Registration (TCTR20230302002).

A Hybrid CNN Model for Deep Feature Extraction for Diabetic Retinopathy Detection and Gradation

Diabetic retinopathy (DR) is a complication of prolonged diabetic mellitus causing damage to the micro-vascular system in retina. Computer-aided detection of DR can significantly reduce time, effort, and cost in early diagnosis and thereby restrict further complications. In this paper, we present a deep learning based framework for automated DR stage classification from fundus retinal images.We design and develop a custom build Convolutional Neural Network (CNN) model named Model-IVS to extract meaningful and discriminative features from the retinal fundus images. The proposed hybrid-CNN combines the multi-scale pyramidal feature processing concept of inception model with the convolutional pipeline based feature extraction concept of VGG-Nets and adopts multi-scale feature concatenation based short-cut connections of DenseNet with learnable convolutions. For the binary classification tasks, we employ Model-IVS as a feature extractor and use Support Vector Machine (SVM) classifier on the reduced features obtained through principal component analysis. The proposed hybrid model is end-to-end trained incrementally on a class-balanced dataset curated from the train set of EyePACS dataset. The cross-dataset generalization of the proposed hybrid CNN based DR classification framework is evaluated on APTOS, MESSIDOR-1 and MESSIDOR-2 datasets. Experimental results demonstrate that our model has outperformed all the existing state-of-the-art methods for DR severity grading task on APTOS dataset. The proposed Model-IVS has achieved best accuracy, AUC-ROC, and kappa score of 84.33%, 0.978 and 0.899, respectively in DR severity grading task. In binary classification tasks like DR screening and referable DR predictions, our Model-IVS feature extraction network with SVM classifier on PCA features has also achieved comparable performance results w.r.t. the state-of-the-art methods. In DR screening task, we recorded an accuracy of 97.84%, 87.42%, and 89.67% on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively. In referable DR prediction, we achieved AUC-ROC score of 0.987, 0.928, and 0.873 on APTOS, MESSIDOR-1, and MESSIDOR-2 datasets, respectively.

Variability in Grading Diabetic Retinopathy Using Retinal Photography and Its Comparison with an Automated Deep Learning Diabetic Retinopathy Screening Software.

Diabetic retinopathy (DR) screening using colour retinal photographs is cost-effective and time-efficient. In real-world clinical settings, DR severity is frequently graded by individuals of different expertise levels. We aim to determine the agreement in DR severity grading between human graders of varying expertise and an automated deep learning DR screening software (ADLS). Using the International Clinical DR Disease Severity Scale, two hundred macula-centred fundus photographs were graded by retinal specialists, ophthalmology residents, family medicine physicians, medical students, and the ADLS. Based on referral urgency, referral grading was divided into no referral, non-urgent referral, and urgent referral to an ophthalmologist. Inter-observer and intra-group variations were analysed using Gwet's agreement coefficient, and the performance of ADLS was evaluated using sensitivity and specificity. The agreement coefficient for inter-observer and intra-group variability ranged from fair to very good, and moderate to good, respectively. The ADLS showed a high area under curve of 0.879, 0.714, and 0.836 for non-referable DR, non-urgent referable DR, and urgent referable DR, respectively, with varying sensitivity and specificity values. Inter-observer and intra-group agreements among human graders vary widely, but ADLS is a reliable and reasonably sensitive tool for mass screening to detect referable DR and urgent referable DR.

DRFL: Federated Learning in Diabetic Retinopathy Grading Using Fundus Images

Diabetic retinopathy (DR) is a complication of diabetic Mellitus, developing retinal lesions that impair vision. The DR detection in the early stages avoids permanent vision loss. The treatments provide relief, and the vision loss due to DR is irreversible. The manual grading of DR is time-consuming and prone to human errors. The other real-time problem is exchanging patient fundus image information with hospitals worldwide while upholding the organisations' privacy concerns. When training a deep learning (DL) network, two critical factors to keep in mind are creating a collaborative platform and protecting patient data privacy. Therefore, an automated DR detection technique is required while protecting patient data and privacy. In this work, we propose a novel DR severity grading technique based on Federated Learning (FL), a recent advancement in DL called DRFL. FL is a new research paradigm that allows DL models to be trained collectively without disclosing clinical information. In DRFL, we combined the Federated averaging (FedAvg) technique and the median of the categorical cross-entropy loss. Since in comparison to FedAvg, the median cross-entropy is better suited for either under-fitted or over-fitted clients. Also, we propose a novel central server that extracts multi-scale features from the fundus images to identify small lesions present in the fundus image. In this work, we consider five clients holding different preprocessed fundus images collected from publicly available databases such as MESSIDOR-2, IDRiD, Kaggle, and a local database collected from Silchar Medical College and Hospital. The proposed model obtained an accuracy of 98.6%, specificity of 99.3%, precision of 97.25%, and an F1 score of 97.5%, which are better results than other techniques.

Robust Collaborative Learning of Patch-Level and Image-Level Annotations for Diabetic Retinopathy Grading From Fundus Image

Diabetic retinopathy (DR) grading from fundus images has attracted increasing interest in both academic and industrial communities. Most convolutional neural network-based algorithms treat DR grading as a classification task via image-level annotations. However, these algorithms have not fully explored the valuable information in the DR-related lesions. In this article, we present a robust framework, which collaboratively utilizes patch-level and image-level annotations, for DR severity grading. By an end-to-end optimization, this framework can bidirectionally exchange the fine-grained lesion and image-level grade information. As a result, it exploits more discriminative features for DR grading. The proposed framework shows better performance than the recent state-of-the-art algorithms and three clinical ophthalmologists with over nine years of experience. By testing on datasets of different distributions (such as label and camera), we prove that our algorithm is robust when facing image quality and distribution variations that commonly exist in real-world practice. We inspect the proposed framework through extensive ablation studies to indicate the effectiveness and necessity of each motivation. The code and some valuable annotations are now publicly available.

The Association Between HbA1c and Other Biomarkers With the Prevalence and Severity of Diabetic Retinopathy.

Introduction: Diabetes mellitus (DM) is considered to be a significant public health problem globally. According to the American Society of Retina Specialists, diabetic retinopathy (DR) is a complication of diabetes that causes damage to the blood vessels of the retina. In a Japanese study showed that HbA1c and fasting blood glucose values can be considered as predictors for the future development of DR. Thus, this study aimed to determine the prevalence and severity of DR among diabetic patients in Medina, Saudi Arabia, and to assess its relationship with HbA1c and other biomarkers.Methods: This cross-sectional study was conducted at Prince Abdulaziz Bin Majed Diabetes Center and Charitable Healthcare Society in Medina, Saudi Arabia, in July 2018. The data were collected from direct interview questionnaires that were administered to 130 randomly selected diabetic subjects. The subjects’ demographic information, eye disease history, medical backgrounds, and laboratory biomarkers were noted. Fundus examinations using a slit lamp were conducted by ophthalmic physicians to diagnose and grade DR. The data were analyzed using Statistical Package for Social Sciences (SPSS) (IBM Corp., Armonk, NY, USA).Results: All 130 diabetic patients were examined for DR. DR was prevalent among 35 (26.9%) of the participants. According to the DR severity grading, 95 (73.1%) had no apparent DR, 11 (8.5%) had mild non-proliferative diabetic retinopathy (NPDR), 11 (8.5%) had moderate NPDR, 11 (8.5%) had severe NPDR, and only two (1.5%) had proliferative diabetic retinopathy (PDR). There was a significant association between the development of DR and HbA1c levels (p = 0.040). The duration of DM was also determined to be a significant risk factor for DR (p = 0.001). No other factors were found to have a significant association with DR.Conclusion: Around one-third of the participants in our study had DR. HbA1c levels and duration of DM were established as important risk factors for DR. Screening is necessary, even in patients with good HbA1c levels, to avoid the late presentation of severe DR and to prevent blindness.

Hierarchical severity grade classification of non-proliferative diabetic retinopathy

Curability of diabetic retinopathy (DR) abnormalities highly rely on regular monitoring, early-stage diagnosis and timely treatment. Detection and analysis of variation in eye images can help the patient to take the early action before progression of the disease. Vision loss can be effectively prevented by automated diagnostic system that assist the ophthalmologists who otherwise practice manual lesion detection processes which are tedious and time-consuming. This paper proposes a hierarchical severity level grading (HSG) system for the detection and classification of DR ailments. The retinal fundus images in the proposed HSG system are categorized as grade 0 (indicating Non-DR class) and DR severity grades 1, 2, 3 depending upon the number of anomalies; microaneurysms and haemorrhages in the fundus images. The challenge of retinal landmark segmentation, DR retinal discrimination and DR severity grading have been addressed in this work contributing to the novelty of the proposed approach. For non-DR and DR classification, the proposed system achieves an overall accuracy of 98.10% by SVM classifier and 100% by kNN classifier. Hierarchal discrimination into further grades of abnormalities resulted in accuracy values of 95.68% and 92.60% with SVM classifier using Gaussian kernel and, 97.90% and 95.30% employing fine kNN classifier. The HSG system demonstrates a clear improvement in accuracy with significantly less computational time comparative to the other state-of-the-art methods when applied to the MESSIDOR dataset. IDRiD dataset is also evaluated for performance validation of the proposed HSG system yielding a maximum of 94.00% classification accuracy using a kNN classifier with a computational time of 0.67 s.

Modified U-Net architecture for semantic segmentation of diabetic retinopathy images

Segmentation of lesions from fundus images is an essential prerequisite for accurate severity assessment of diabetic retinopathy. Due to variation in morphologies, number and size of lesions, the manual grading process becomes extremely challenging and time-consuming. This necessitates the need of an automatic segmentation system that can precisely define the region of interest boundaries and assist ophthalmologists in speedy diagnosis along with diabetic retinopathy severity grading. The paper presents a modified U-Net architecture based on residual network and employs periodic shuffling with sub-pixel convolution initialized to convolution nearest neighbour resize. The proposed architecture has been trained and validated for microaneurysm and hard exudate segmentation on two publicly available datasets namely IDRiD and e-ophtha. For IDRiD dataset, the network obtains 99.88% accuracy, 99.85% sensitivity, 99.95% specificity and dice score of 0.9998 for both microaneurysm and exudate segmentation. Further, when trained on e-ophtha and validated on IDRiD dataset, the network shows 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9998 for microaneurysm segmentation. For exudates segmentation, the model obtained 99.98% accuracy, 99.88% sensitivity, 99.89% specificity and dice score of 0.9999, when trained on e-ophtha and validated on IDRiD dataset. In comparison to existing literature, the proposed model provides state-of-the-art results for retinal lesion segmentation.

DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

Diabetic retinopathy (DR) grading is crucial in determining the adequate treatment and follow up of patient, but the screening process can be tiresome and prone to errors. Deep learning approaches have shown promising performance as computer-aided diagnosis (CAD) systems, but their black-box behaviour hinders clinical application. We propose DR|GRADUATE, a novel deep learning-based DR grading CAD system that supports its decision by providing a medically interpretable explanation and an estimation of how uncertain that prediction is, allowing the ophthalmologist to measure how much that decision should be trusted. We designed DR|GRADUATE taking into account the ordinal nature of the DR grading problem. A novel Gaussian-sampling approach built upon a Multiple Instance Learning framework allow DR|GRADUATE to infer an image grade associated with an explanation map and a prediction uncertainty while being trained only with image-wise labels. DR|GRADUATE was trained on the Kaggle DR detection training set and evaluated across multiple datasets. In DR grading, a quadratic-weighted Cohen's kappa (κ) between 0.71 and 0.84 was achieved in five different datasets. We show that high κ values occur for images with low prediction uncertainty, thus indicating that this uncertainty is a valid measure of the predictions' quality. Further, bad quality images are generally associated with higher uncertainties, showing that images not suitable for diagnosis indeed lead to less trustworthy predictions. Additionally, tests on unfamiliar medical image data types suggest that DR|GRADUATE allows outlier detection. The attention maps generally highlight regions of interest for diagnosis. These results show the great potential of DR|GRADUATE as a second-opinion system in DR severity grading.

602-P: Explaining an Artificial Intelligence (AI) System for Diabetic Retinopathy (DR) Screening in Primary Care

We have developed a novel technique to explain results of an AI system and demonstrate its ability in explaining the EyeArt AI eye screening system for DR. Besides providing clinically consistent and accurate results, AI systems in healthcare must be explainable (be able to provide reasons for their decisions). This is paramount in making them trustworthy. The EyeArt system is intended for use by healthcare providers to screen for referable DR using color fundus photographs from 18 years or older diabetic patients who do not have persistent visual impairment. It is designed to provide screening results in under a minute and enable DR screening at point of care in endocrinology and primary care clinics. Figure shows that the explainability technique highlights image regions that most significantly contribute to the EyeArt system’s results. These highlighted regions correspond to lesions marked by an expert human grader. In a previous study on 107,001 consecutive patient visits, the EyeArt system has been shown to achieve sensitivity of 91.3% (95% CI: 90.9%-91.7%), specificity of 91.1% (95% CI: 90.9%-91.3%), NPV of 97.6% (95% CI: 97.5%-97.7%), and PPV of 72.5% (95% CI: 71.9%-73.0%). The work presented here provides evidence that the EyeArt system is explainable and has been designed to report DR screening results based on lesions considered important by the ophthalmology community for DR severity grading. Disclosure N. Parekh: Employee; Self; Eyenuk Inc. M. Bhaskaranand: Employee; Self; Eyenuk Inc. C. Ramachandra: Employee; Self; Eyenuk Inc. S. Bhat: Employee; Self; Eyenuk Inc. K. Solanki: Employee; Self; Eyenuk Inc. Stock/Shareholder; Self; Eyenuk Inc. Funding National Institutes of Health

Assessment of diabetic retinopathy using two ultra-wide-field fundus imaging systems, the Clarus\xae and Optos\u2122 systems

BackgroundThe ability to image wide fundus fields and to conduct swift, non-invasive examinations is increasingly important with the escalation in patients with diabetic retinopathy (DR).MethodsFifty eyes of 28 consecutive patients with DR were examined in this prospective observational study. A total of 46 eyes, 25 right and 21 left eyes, of 27 patients (male, 19; female, 8) were ultimately included in the analysis. All patients underwent comprehensive ophthalmological examination. A single image each was obtained using two ultra-wide-field (UWF) imaging systems: Optos® (Optos Carfornia®, Optos PLC, Dunfermline, United Kingdom) and Clarus™ (CLARUS 500™, Carl Zeiss Meditec Inc., Californea, USA), without mydriasis. The total retinal area captured and the obscured retinal area were compared between the two systems using nonparametric Wilcoxon matched-pairs signed-rank analysis. Early Treatment of Diabetic Retinopathy Study (ETDRS) and International Clinical DR severity were analyzed by κ statistics.ResultsThe Optos® allowed capture of larger areas of the fundus than the Clarus™ (465 ± 117 vs. 243 ± 39 disc areas, P < 0.0001). In 85% (39/46) of Optos® images and 7% (3/46) of Clarus™ images, a slightly obscured area was observed within the ETDRS-7 field area. κ values for ETDRS DR severity and International Clinical DR severity between the Optos® and Clarus™ images were 0.88 and 0.79, respectively. Severity was higher according to Clarus™ images in two eyes in which the ETDRS DR severity grading differed between the systems. Severity was higher in four Clarus™ images and in a single Optos® image in five eyes in which the International Clinical DR severity grading differed between the systems.ConclusionThe Optos® and Clarus™ UWF retinal imaging systems were useful for examining eyes with DR, using single images obtained without mydriasis. The systems were both generally consistent in assessing DR severity, with some partial discrepancies. It is important to understand the characteristics of each respective UWF retinal imaging system when using them to assess DR.

Association of serum vitamin D levels and diabetic retinopathy in Asian Indians with type 2 diabetes

BackgroundVitamin D deficiency (VDD) is a condition that has been associated with diabetic retinopathy (DR) in various populations, but has not been studied in Asian Indians. AimsTo evaluate the association of serum 25-hydroxyvitamin D (25(OH)D) levels with presence and severity of DR among Asian Indians with type 2 diabetes. MethodsWe collected information on individuals with type 2 diabetes that received care at a tertiary diabetes centre in India, between 2012 and 2015. Patients were 18 years of age or older, underwent retinal examinations with DR severity grading and had serum 25(OH)D measurements. ResultsSerum 25(OH)D levels were lower in patients with retinopathy compared to those without (11.9 ± 2.2 ng/ml vs. 13.7 ± 2.1 ng/ml, p < 0.001). Stratifying patients by DR grade, reduced geometric means of 25(OH)D levels were associated with increased retinopathy severity. After adjusting for six key covariates, VDD was associated with increased rates of proliferative DR (OR 2.05; 95% CI 1.35–3.11; p = 0.001). ConclusionsIn Asian Indians with type 2 diabetes, lower serum 25(OH)D was associated with increased severity of DR and the presence of VDD was associated with a two-fold increased risk for proliferative DR.

Prevalence of Diabetic Retinopathy in Urban Slums: The Aditya Jyot Diabetic Retinopathy in Urban Mumbai Slums Study—Report 2

ABSTRACTObjectives: The aims of the study were to estimate the prevalence of diabetic retinopathy (DR) and enumerate history-based risk factors in the urban slums of Western India.Methods: The population-based study was conducted in seven wards of Mumbai urban slums, where we screened 6569 subjects of ≥ 40 years age, with a response rate of 98.4%, for type 2 diabetes mellitus (T2DM) based on American Diabetes Association criteria. All subjects with T2DM underwent dilated 30° seven-field stereo-fundus-photography for DR severity grading based on modified Airlie House classification. A multivariate logistic regression model was used to assess the correlation of DR with the history-based risk factors.Results: The prevalence of DR in the general population of Mumbai urban slums was 1.41% (95% CI 0.59–2.23) and in the T2DM population it was 15.37% (95% CI 8.87–21.87). The positive associations with DR were the longer duration of DM (≥ 11 years: OR, 12.77; 95% CI 2.93–55.61) and male gender (OR, 2.05; 95% CI 1.08–3.89); increasing severity of retinopathy was also significantly associated with longer duration of DM (p < 0.001). However, history of hypertension, family history of DM, consanguineous marriage and migration status were not associated with DR in the study population.Conclusions: The prevalence of DR in the general population and T2DM subjects were 1.41% and 15.37% respectively in Mumbai urban slums. Duration of DM and male gender were significantly associated with DR. The slums in Western India show the trends of urban lifestyle influences similar to the rest of urban India.

DREAM: diabetic retinopathy analysis using machine learning.

This paper presents a computer-aided screening system (DREAM) that analyzes fundus images with varying illumination and fields of view, and generates a severity grade for diabetic retinopathy (DR) using machine learning. Classifiers such as the Gaussian Mixture model (GMM), k-nearest neighbor (kNN), support vector machine (SVM), and AdaBoost are analyzed for classifying retinopathy lesions from nonlesions. GMM and kNN classifiers are found to be the best classifiers for bright and red lesion classification, respectively. A main contribution of this paper is the reduction in the number of features used for lesion classification by feature ranking using Adaboost where 30 top features are selected out of 78. A novel two-step hierarchical classification approach is proposed where the nonlesions or false positives are rejected in the first step. In the second step, the bright lesions are classified as hard exudates and cotton wool spots, and the red lesions are classified as hemorrhages and micro-aneurysms. This lesion classification problem deals with unbalanced datasets and SVM or combination classifiers derived from SVM using the Dempster-Shafer theory are found to incur more classification error than the GMM and kNN classifiers due to the data imbalance. The DR severity grading system is tested on 1200 images from the publicly available MESSIDOR dataset. The DREAM system achieves 100% sensitivity, 53.16% specificity, and 0.904 AUC, compared to the best reported 96% sensitivity, 51% specificity, and 0.875 AUC, for classifying images as with or without DR. The feature reduction further reduces the average computation time for DR severity per image from 59.54 to 3.46 s.

Automatic Detection of Exudates Using Morphological Approach

Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina .The blindness due to DR can be prevented if detected early enough for treatment.Hence screening for early stage of DR is very important. An ophthalmologist uses an ophthalmoscope to visualize the blood vessels and his or her brain to detect the DR stages. The above pathology-based method is time consuming and often requires fluorescein angiograms for accurate diagnosis. It requires highly trained and skilled clinicians to perform the DR severity grading method. In this paper we have proposed a low cost retinal diagnosis system which can aid an ophthalmologist to quickly diagnose various stages of diabetic retinopathies.