Grading Of Diabetic Macular Edema Research Articles

Arithmetic Optimization for Coinciding Diabetic Retinopathy and Diabetic Macular Edema Grading based on Self-Attention Convolutional Neural Network

This paper proposes a Self-Attention Convolutional Neural Network (SACNN) optimized with Arithmetic Optimization Algorithm (AOA) for coinciding Diabetic Retinopathy (DR) and Diabetic Macular Edema Grading (DMEG) (SACNN-AOA-DR-DMEG). Initially, the input image is collected from 2 openly available benchmark datasets, namely Messidor and ISBI 2018 IDRiD. Then the input image is pre-processing using Altered Phase Preserving Dynamic Range Compression (APPDRC) for reducing noise from the imageries. SACNN receives the pre-processed imageries. The SACNN has three modules: (i) plane attention module, (ii) depth attention module, (iii) Attention Fusion Module. DR and DME features are extracted by plane attention module and depth attention module of SACNN. Attention Fusion Module receives extracted characteristics for categorizing and grading DR and DME disorders. SACNN does not adopt any optimization techniques to guarantee accurate DR and DME grading disorders. That’s why, Arithmetic Optimization Algorithm (AOA) is deemed to optimize the SACNN weight parameters. The proposed technique is implemented in Python. The proposed SACNN-AOA-DR-DMEG method provides 11.18%, 18.99% and 23.76% higher accuracy for diabetic retinopathy grading; 11.52%, 29.62% and 20.38% higher accuracy for DMEG; 33.39%, 22%, 39.26% lower computation time on Messidor data compared with the existing methods, such as AMGNN-DR-DMEG, LCNN-DR-DMEG, and FFN-DR-DMEG respectively.

Optical Coherence Tomography-Based Grading of Diabetic Macular Edema Is Associated with Systemic Inflammatory Indices and Imaging Biomarkers

Introduction: Objectives of the study were to investigate the correlation between optical coherence tomography (OCT)-based grading of diabetic macular edema (DME) and systemic inflammatory indices, imaging biomarkers, and early anti-vascular endothelial growth factor (VEGF) treatment response. Methods: A total of 111 eyes from 111 patients with DME treated with intravitreous anti-VEGF therapy for 3 consecutive months every month were enrolled in this retrospective study. According to a protocol termed “TCED,” DME was divided into early, advanced, severe, and atrophic stages. The best-corrected visual acuity (BCVA), subretinal fluid (SRF), and the number of hyperreflective foci (HRF) in the whole retinal layers were analyzed at baseline and 3 months after the first injection. Peripheral blood inflammatory indices were calculated, including neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), platelet (PLT)-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), and C-reactive protein (CRP). Statistical analysis was performed to compare the visual and anatomical results and evaluate HRF and SRF in different stages of DME before and after treatment. Results: There were significant differences in systemic inflammatory indices among the four groups, including NLR, PLR, MLR, SII, and CRP (all p < 0.05). The CRP, NLR, PLR, MLR, and SII were significantly higher in the atrophic stage compared to the advanced stage (all p < 0.05). Conversely, the CRP, NLR, PLR, MLR, and SII were significantly lower in the advanced stage compared to the early stage (all p < 0.05). Except for the atrophic stage, BCVA and central retinal thickness (CRT) were significantly improved after treatment in early, advanced and severe stages (all p < 0.05), especially in the severe stage. The decline in the proportion of SRF and HRF ≥20 was the most significant in the advanced stage after anti-VEGF treatment (p < 0.001, p = 0.016), but not in the early and severe stages (all p > 0.05). Conclusion: Systemic inflammatory indices and the decline in the proportion of SRF and HRF ≥20 were closely associated with different stages of DME based on “TCED.” Meanwhile, the “TCED” grading system can predict visual and anatomical prognosis of DME after anti-VEGF treatment, which may be a biomarker for identifying risk stratification and management of DME.

A Multi-Task Learning and Multi-Branch Network for DR and DME Joint Grading

Diabetic Retinopathy (DR) is one of the most common microvascular complications of diabetes. Diabetic Macular Edema (DME) is a concomitant symptom of DR. As the grade of lesion of DR and DME increase, the possibility of blindness can also increase significantly. In order to take the early interventions as soon as possible to reduce the likelihood of blindness, it is necessary to perform both DR and DME grading. We design a joint grading model based on multi-task learning and multi-branch networks (MaMNet) for DR and DME grading. The model mainly includes a multi-branch network (MbN), a feature fusion module, and a disease classification module. The MbN is formed by four branch structures, which can extract the low-level feature information of DME and DR in a targeted way; the feature fusion module is composed of a self-feature extraction module (SFEN), cross-feature extraction module (CFEN) and atrous spatial pyramid pooling module (ASPP). By combining various features collected from the aforementioned modules, the feature fusion module can provide more thorough discriminative features, which benefits the joint grading accuracy. The ISBI-2018-IDRiD challenge dataset is used to evaluate the performance of the proposed model. The experimental results show that based on the multi-task strategy the two grading tasks of DR and DME can provide each other with additional useful information. The joint accuracy of the model, the accuracy of DR and the accuracy of DME are 61.2%, 64.1% and 79.4% respectively.

Joint DR-DME grading classification using optimal feature selection-based deep graph correlation network

Diabetic macular edema (DME) and diabetic retinopathy (DR) are the leading causes of human blindness, and accurate grading of individual DME, individual DR, and the joint DR-DME is very important for the diagnosis of human eye diseases. However, the conventional methods failed to separate the features such as disease-specific, disease-dependent, and joint DR-DME, which resulted in poor grading accuracy. In addition, optimal feature selection is also vital in DR-DME grading classification for improving the performance of joint DR-DME grading classification. Therefore, this work focuses on the implementation of an advanced deep graph correlation learning model based on a joint DR-DME network (JDD-Net) for disease detection and classification from color fundus images. Initially, convolutional block attention module (CBAM) and joint disease attention (JDA) modules are combined to extract the DR-specific, DME-specific, and joint DR-DME disease-dependent features. Here, interdependent DR and DME features are separated by a CBAM-based channel-spatial split attention mechanism. In addition, an iterative random forest network (IRF-Net) is used to select the optimal features by adopting fast machine learning properties. Finally, a deep graph correlation network (DGCN) is used to classify the different diseases using a pre-trained model. The simulations conducted on the Indian Diabetic Retinopathy Image Dataset (IDRiD) disclose that the proposed JDD-Net results in improved individual DR, individual DME, and joint DR-DME performance as compared to state-of-the-art approaches with DR, DME, and joint DR-DME accuracy of 99.53%, 99.1%, and 99.01%, respectively.

A comprehensive computer-aided system for an early-stage diagnosis and classification of diabetic macular edema

Diabetic macular edema (DME) is a condition of retinal swelling due to the accumulation of leaked plasma in the extracellular space in the retina, known as the macula. DME is a chronic progressive retinal disorder that likely results in permanent complete blindness. The early signs of DME are not discernible by merely suspecting the fundus picture with the naked eye. Therefore, a computer-assisted diagnostic system could aid ophthalmologists in screening, diagnosing, and treating DME. This study proposes an efficient and complete model for early diagnosis and staging of DME. To overcome the challenges in precise localization of fovea, blood vessel network extraction, and accurate lesion segmentation, improved image relative subtraction, Gabor wavelet filter, and novel advanced fuzzy c-means clustering algorithms are introduced, respectively. Finally, the Bayesian classifier using the Gaussian function with expectation maximization is used for DME grading. The accurate optic disc and fovea localization, exudates’ segmentation, and classification improved the overall system’s performance. The proposed model achieves an average accuracy of 96.17%, 98.60%, 97.85%, and 98.80% for optic disc detection, fovea localization, exudates segmentation, and DME classification, respectively. The performance of the proposed model compared to the competitive studies illustrates the superiority of the suggested methodology.

A reinforcement learning approach for VQA validation: An application to diabetic macular edema grading.

Recent advances in machine learning models have greatly increased the performance of automated methods in medical image analysis. However, the internal functioning of such models is largely hidden, which hinders their integration in clinical practice. Explainability and trust are viewed as important aspects of modern methods, for the latter's widespread use in clinical communities. As such, validation of machine learning models represents an important aspect and yet, most methods are only validated in a limited way. In this work, we focus on providing a richer and more appropriate validation approach for highly powerful Visual Question Answering (VQA) algorithms. To better understand the performance of these methods, which answer arbitrary questions related to images, this work focuses on an automatic visual Turing test (VTT). That is, we propose an automatic adaptive questioning method, that aims to expose the reasoning behavior of a VQA algorithm. Specifically, we introduce a reinforcement learning (RL) agent that observes the history of previously asked questions, and uses it to select the next question to pose. We demonstrate our approach in the context of evaluating algorithms that automatically answer questions related to diabetic macular edema (DME) grading. The experiments show that such an agent has similar behavior to a clinician, whereby asking questions that are relevant to key clinical concepts.

A Novel original feature fusion network for joint diabetic retinopathy and diabetic Macular edema grading

A Novel original feature fusion network for joint diabetic retinopathy and diabetic Macular edema grading

Auto-Metric Graph Neural Network optimized with Capuchin search optimization algorithm for coinciding diabetic retinopathy and diabetic Macular edema grading

Diabetic retinopathy (DR) and diabetic macular edema (DME) are the major eternal blindness in aged people. In this manuscript, Auto-Metric Graph Neural Network (AGNN) optimized with Capuchin search optimization algorithm is proposed for coinciding DR and DME grading (AGNN-CSO-DR-DME). The novelty of this work is to identify the Diabetic retinopathy and diabetic macular edema grading at initial stage with higher accuracy by decreasing the error rate and computation time. Initially, input image is taken from two public benchmark datasets that is ISBI 2018 imbalanced diabetic retinopathy grading dataset and Messidor dataset. Then, the input fundus image is pre-processed by APPDRC filtering method removes noise in input images. Also, the pre-processed images are given to the Gray level co-occurrence matrix (GLCM) window adaptive algorithm based feature extraction method. The extracted features of the DR and DME are fed to AGNN for classifying the grading of both DR and DME diseases. Generally, AGNN not reveal any adoption of optimization methods compute optimum parameters for assuring correct grading of both DR and DME diseases. Thus, CSOA is used for optimizing the AGNN weight parameters. The proposed method is carried out in python, its efficiency is assessed under performances metrics, such as f-measure, execution time and accuracy. The proposed method attains higher accuracy in ISBI 2018 IDRiD dataset 99.57 %, 97.28 %, and 96.34 %, compared with existing methods, like CANet-DR-DME, HDLCNN-MGMO-DR-DME, ANN-DR-DME and 91.17 %, 96.52 % and 97.36 %higher accuracy in Messidor dataset compared with existing methods, like CANet-DR-DME, TCNN-DR-DME, and 2-d-FBSE-FAWT-DR-DME.

Automatic grading of Diabetic macular edema based on end-to-end network

Diabetic macular edema (DME) is one of the main causes of permanent blindness. Automatic grading is helpful to quick diagnosis of DME and reduction of vision loss. Most of the existing methods grade DME according to the shortest distance from the hard exudates(HEs) to the fovea, which is required to detect the fovea and HEs beforehand. The end-to-end network takes the whole fundus image as input to obtain the grading result, but the accuracy is often low because of the complexity of DME. Some end-to-end architectures simplify the grading to two grades instead of three grades or use other disease information to improve the accuracy. In order to improve the efficiency and accuracy of grading without introducing the lesion segmentation or simplifying the grading task, this paper proposes a new end-to-end architecture with ResNet50 combined with channel attention (SENet) to extract features and introduces the disease attention module to supplement the disease-specific information of DME, which can achieve higher grading results and reduce the grading cost without additional acquisition of fovea and HEs. In order to solve the problem of class imbalance and insufficient training samples in grading, this paper adds class weight to the crossentropy function in the design of the loss function and augmentation techniques to expand data. The proposed network is verified on the MESSIDOR dataset and has a good grading result. The experimental results show that the proposed method has high accuracy, specificity, sensitivity and F1 score, which are 97.06%, 98.97%, 88.64% and 0.9177, respectively.

CCNET: Cross Coordinate Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading.

With the rapid development of the world economy and increasing improvement of people's living standards, the number of diabetic patients has been growing quickly. Meanwhile, the complications of diabetes especially retinopathy have been affecting their daily life seriously. The only way to prevent it from getting worse and even leading to blindness is to make corresponding diagnosis as early as possible. However, it's extremely impossible for professionals to diagnose all the patients through their fundus images. It couldn't be better to solve the problem by automatic systems, so we present a novel network to learn the features of diabetic retinopathy (DR) and its complication diabetic macular edema (DME) and the relationship between them, focus on some vital areas in the pictures and eventually obtain the grades of the two diseases at the same time. Experimental results further prove the effectiveness of our proposed module comparing to the only joint grading network before.

GRAding of functional and anatomical response to DExamethasone implant in patients with Diabetic Macular Edema: GRADE-DME Study

To analyze functional and anatomical response patterns to dexamethasone (DEX) implant in diabetic macular edema (DME), to describe proportion of responders and non-responders, and to propose a new DME grading system. Retrospective, multicenter, observational cohort study. Naïve and non-naïve DME patients were treated with DEX, with visual acuity (VA) ≥ 0.2 logMAR and central subfield thickness (CST) of ≥ 300 µm. Functional and anatomical responses were graded after 2 and 4 months, and categorized as early and stable improvement, early and progressive improvement, pendular response, delayed improvement, and persistent non-response. 417 eyes were included (175 treatment naïve eyes). Compared to non-naïve eyes, naïve eyes showed a very good functional response (VA gain ≥ 10 letters) more frequently after 2 and 4 months (56% and 57% [naïve] vs. 33% and 28% [non-naïve], p < 0.001). A VA gain < 5 letters (non-response) after 2 and 4 months was seen in 18% and 16% of naïve eyes, and in 49% and 53% of non-naïve eyes (p < 0.001). A lack of anatomical response was rare in both groups, but more frequently in non-naïve eyes (12% vs. 4%, p = 0.003). Functionally and anatomically, naïve eyes showed most frequently an early and stable improvement (functionally: 77/175 44%; anatomically: 123/175 eyes, 70%). Most non-naïve eyes experienced no significant improvement functionally (97/242 eyes, 40%), despite a mostly early and stable improvement anatomical response pattern (102/242 eyes, 42%). Functional but not anatomical response patterns were influenced by baseline VA. Naïve and non-naïve eyes show different functional and anatomical response patterns to DEX implant. Functional non-responders are rare in naïve eyes, whereas anatomical non-response is unusual in both groups.

OctNET: A Lightweight CNN for Retinal Disease Classification from Optical Coherence Tomography Images

Background and ObjectiveRetinal diseases are becoming a major health problem in recent years. Their early detection and ensuing treatment are essential to prevent visual damage, as the number of people affected by diabetes is expected to grow exponentially. Retinal diseases progress slowly, without any discernible symptoms. Optical Coherence Tomography (OCT) is a diagnostic tool capable of analyzing and identifying the quantitative discrimination in the disease affected retinal layers with high resolution. This paper proposes a deep neural network-based classifier for the computer-aided classification of Diabetic Macular Edema (DME), drusen, Choroidal NeoVascularization (CNV) from normal OCT images of the retina. MethodsIn the proposed method, we demonstrate the feasibility of classifying and detecting severe retinal pathologies from OCT images using a deep convolutional neural network having six convolutional blocks. The classification results are explained using a gradient-based class activation mapping algorithm. ResultsTraining and validation of the model are performed on a public dataset of 83,484 images with expert-level disease grading of CNV, DME, and drusen, in addition to normal retinal image. We achieved a precision of 99.69%, recall of 99.69%, and accuracy of 99.69% with only three misclassifications out of 968 test cases. ConclusionIn the proposed work, downsampling and weight sharing were introduced to improve the training efficiency and were found to reduce the trainable parameters significantly. The class activation mapping was also performed, and the output image was similar to the retina’s actual color OCT images. The proposed network used only 6.9% of learnable parameters compared to the existing ResNet-50 model and yet outperformed it in classification. The proposed work can be potentially employed in real-time applications due to reduced complexity and fewer learnable parameters over other models.

Diabetic macular edema grading based on improved Faster R-CNN and MD-ResNet

Diabetic macular edema (DME) is the main cause of visual impairment in diabetic patients. Early detection of DME will significantly reduce the risk of vision loss for the patients. According to the clinical DME grading standard, the positional relationship between Hard Exudates (HEs) and macular center is an important basis for DME grading. Accurate DME grading is thus predicated on properly locating the macular center and segmenting HEs. HEI-MED and E-ophtha EX data sets were tested by the proposed DME grading method, reaching an average accuracy of 94.4% and 87%, respectively. The proposed method was also tested by comparison against other commonly used methods as per its potential to assist doctors in initially screening DME; it was found to not only improve the efficiency of DME detection, but also to save Optical Coherence Tomography medical resources over the other methods tested.

A Robust and Rotation Invariant Automated Algorithm for Grading Diabetic Macular Edema in Retinal Images

In this work, an algorithm for grading Diabetic Macular edema is projected for diagnosing the severity of disease. One of the major contributions is that, the algorithm is invariant to the rotation of retinal image. The projected research work includes the segmentation of Optic disk, localization of Macula, segmentation of exudates and Grading of Diabetic Macular Edema into Severe, moderate and No disease. Rotation Invariance and Less time complexity make the work more efficient. The projected method is highly precise with high precision, recall and F-Measure values. A set of NPDR (Non Proliferative Diabetic Retinopathy) database is used for the proposed algorithm.

CANet: Cross-Disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading.

Diabetic retinopathy (DR) and diabetic macular edema (DME) are the leading causes of permanent blindness in the working-age population. Automatic grading of DR and DME helps ophthalmologists design tailored treatments to patients, thus is of vital importance in the clinical practice. However, prior works either grade DR or DME, and ignore the correlation between DR and its complication, i.e., DME. Moreover, the location information, e.g., macula and soft hard exhaust annotations, are widely used as a prior for grading. Such annotations are costly to obtain, hence it is desirable to develop automatic grading methods with only image-level supervision. In this article, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision. Our key contributions include the disease-specific attention module to selectively learn useful features for individual diseases, and the disease-dependent attention module to further capture the internal relationship between the two diseases. We integrate these two attention modules in a deep network to produce disease-specific and disease-dependent features, and to maximize the overall performance jointly for grading DR and DME. We evaluate our network on two public benchmark datasets, i.e., ISBI 2018 IDRiD challenge dataset and Messidor dataset. Our method achieves the best result on the ISBI 2018 IDRiD challenge dataset and outperforms other methods on the Messidor dataset. Our code is publicly available at https://github.com/xmengli999/CANet.

Diabetic macular edema grading in retinal images using vector quantization and semi-supervised learning

BACKGROUND: Diabetic macular edema (DME) is one of the severe complication of diabetic retinopathy causing severe vision loss and leads to blindness in severe cases if left untreated.OBJECTIVE:To grade the severity of DME in retinal images.METHODS:Firstly, the macular is localized using its anatomical features and the information of the macula location with respect to the optic disc. Secondly, a novel method for the exudates detection is proposed. The possible exudate regions are segmented using vector quantization technique and formulated using a set of feature vectors. A semi-supervised learning with graph based classifier is employed to identify the true exudates. Thirdly, the disease severity is graded into different stages based on the location of exudates and the macula coordinates.RESULTS:The results are obtained with the mean value of 0.975 and 0.942 for accuracy and F1-scrore, respectively.CONCLUSION:The present work contributes to macula localization, exudate candidate identification with vector quantization and exudate candidate classification with semi-supervised learning. The proposed method and the state-of-the-art approaches are compared in terms of performance, and experimental results show the proposed system overcomes the challenge of the DME grading and demonstrate a promising effectiveness.

A 5-year prospective study of type 2 diabetes patients in Shanghai Xinjing Community 3.The regression and promoting factors of diabetic retinopathy and diabetic macular edema in Chinese type 2 diabetes patients

Background Long-term study on type 2 diabetes discovered that some patients with diabetic retinopathy (DR) or diabetic macular edema (DME) appear regression of lesions without invasive ocular intervention but only systemic medication.These mechanisms remain unclear. Objective This study was to survey the regression rate and relevant factors of DR and DME in type 2 diabetic patients. Methods A prospectively observational study was performed.Totally 778 patients who met the inclusion criteria participated in this consecutive 5-year survey.The demographic information of the patients was collected, and the systemic and ophthalmological examinations were carried out, and the fundus photography was identified by 2 doctors by blind method.DR was graded into non-, mild-, moderate-, severe-nonproliferation DR and proliferative DR based on international clinical classification, and DME was graded into non-, mild-, moderate-and severe-DME.DR improvement and DME regression were served as the outcome variables and defined as the grading of DR or DME in lateral eyes lowering by at least 1 grade and without development of DR or DME in fellow eyes.The influences of age, gender, education level, diabetes onset age, diabetes course, obesity and serum creatinine, triacylglycerol, total cholesterol and glycosylated hemoglobin levels were evaluated by Logistic regression analysis. Results Four hundred and fifty-six patients appeared DR in the initial examination, of which 139 patients appeared regression of DR severity with the regression rate of 30.48%.Both low blood glucose level and low serum creatinine level at initial examination were independent risk factors associated with DR regression (blood glucose level: odds ratio(OR)=0.53, 95% confidence interval [CI]: 0.45-0.63, P<0.01; serum creatinine level: OR=0.98, 95%CI: 0.97-0.99, P<0.01). One hundred and fifty-eight patients were found to have DME at the initial examination, of which 20 had a regression of DME severity throughout the follow-up duration, with the regression rate 12.66%.High baseline blood glucose level was found to be the only independent risk factor associated with DME regression (OR=1.47, 95%CI: 1.14-1.91, P<0.01). Conclusions Effective control of blood glucose and serum creatinine levels is a favorable factor for the regression of DR, and the rapid drop of blood glucose level is beneficial to the regression of DME. Key words: Diabetes, type 2/complications; Retinopathy, diabetic; Macular edema, diabetic

Computer-assisted grading of diabetic macular edema on retinal color fundus images.

Diabetic macular edema (DME) is one of the vision-impairing manifestations of Diabetic Retinopathy (DR). Early detection and treatment of DME can prevent permanent vision loss in people suffering from DR. However, the clinical detection through biomicroscopy is time-consuming. In this paper, a computer-assisted grading method has been proposed to determine the DME severity based on the spatial distribution of exudative lesions around macula. The region around macula is classified into zonal levels and severity of the DME is graded based on the presence of exudative lesions in each zone. The proposed method has been evaluated on diverse public and local databases, and produced the sensitivity of 89.54% for 9.1 false positive per image (FPPI) for exudate detection and 98.8% accuracy for DME grading.

Application of higher-order spectra for automated grading of diabetic maculopathy.

Diabetic macular edema (DME) is one of the most common causes of visual loss among diabetes mellitus patients. Early detection and successive treatment may improve the visual acuity. DME is mainly graded into non-clinically significant macular edema (NCSME) and clinically significant macular edema according to the location of hard exudates in the macula region. DME can be identified by manual examination of fundus images. It is laborious and resource intensive. Hence, in this work, automated grading of DME is proposed using higher-order spectra (HOS) of Radon transform projections of the fundus images. We have used third-order cumulants and bispectrum magnitude, in this work, as features, and compared their performance. They can capture subtle changes in the fundus image. Spectral regression discriminant analysis (SRDA) reduces feature dimension, and minimum redundancy maximum relevance method is used to rank the significant SRDA components. Ranked features are fed to various supervised classifiers, viz. Naive Bayes, AdaBoost and support vector machine, to discriminate No DME, NCSME and clinically significant macular edema classes. The performance of our system is evaluated using the publicly available MESSIDOR dataset (300 images) and also verified with a local dataset (300 images). Our results show that HOS cumulants and bispectrum magnitude obtained an average accuracy of 95.56 and 94.39% for MESSIDOR dataset and 95.93 and 93.33% for local dataset, respectively.

Automated detection of exudates and macula for grading of diabetic macular edema

Medical systems based on state of the art image processing and pattern recognition techniques are very common now a day. These systems are of prime interest to provide basic health care facilities to patients and support to doctors. Diabetic macular edema is one of the retinal abnormalities in which diabetic patient suffers from severe vision loss due to affected macula. It affects the central vision of the person and causes total blindness in severe cases. In this article, we propose an intelligent system for detection and grading of macular edema to assist the ophthalmologists in early and automated detection of the disease. The proposed system consists of a novel method for accurate detection of macula using a detailed feature set and Gaussian mixtures model based classifier. We also present a new hybrid classifier as an ensemble of Gaussian mixture model and support vector machine for improved exudate detection even in the presence of other bright lesions which eventually leads to reliable classification of input retinal image in different stages of macular edema. The statistical analysis and comparative evaluation of proposed system with existing methods are performed on publicly available standard retinal image databases. The proposed system has achieved average value of 97.3%, 95.9% and 96.8% for sensitivity, specificity and accuracy respectively on both databases.