Diabetic Retinopathy Detection Using Genetic Algorithm-Based CNN Features and Error Correction Output Code SVM Framework Classification Model

It is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can minimise the risk of proliferated diabetic retinopathy, which is the advanced level of this disease, and having higher risk of severe impairment. Therefore, it becomes important to classify DR stages. To this effect, this paper presents a weighted fusion deep learning network (WFDLN) to automatically extract features and classify DR stages from fundus scans. The proposed framework aims to treat the issue of low quality and identify retinopathy symptoms in fundus images. Two channels of fundus images, namely, the contrast-limited adaptive histogram equalization (CLAHE) fundus images and the contrast-enhanced canny edge detection (CECED) fundus images are processed by WFDLN. Fundus-related features of CLAHE images are extracted by fine-tuned Inception V3, whereas the features of CECED fundus images are extracted using fine-tuned VGG-16. Both channels’ outputs are merged in a weighted approach, and softmax classification is used to determine the final recognition result. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method tested on the Messidor dataset reports an accuracy level of 98.5%, sensitivity of 98.9%, and specificity of 98.0%, whereas on the Kaggle dataset, the proposed model reports an accuracy level of 98.0%, sensitivity of 98.7%, and specificity of 97.8%. Compared with other models, our proposed network achieves comparable performance.

Automatic Detection and Classification of Diabetic Retinopathy from Retinal Fundus Images by Abdullah Biran, Master of Applied Science, lectrical and computer engineering Department, Ryerson University, 2017. Diabetic Retinopathy (DR) is an eye disease that leads to blindness when it progresses to proliferative level. The earliest signs of DR are the appearance of red and yellow lesions on the retina called hemorrhages and exudates. Early diagnosis of DR prevents from blindness. In this thesis, an automatic algorithm for detecting diabetic retinopathy is presented. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. In addition, Support Vector Machine (SVM) classifier is used to classify retinal images into normal or abnormal cases of DR including non-proliferative (NPDR) or proliferative diabetic retinopathy (PDR). The proposed method has been tested on fundus images from Standard Diabetic Retinopathy Database (DIARETDB). The implementation of the presented methodology was done in MATLAB. The methodology is tested for sensitivity and accuracy.

INTRODUCTION: Diabetic retinopathy (DR) is one of the consequences of diabetes which if untreated may lead to loss of vision. Generally, for DR detection, retinal images are obtained using a traditional fundus camera. A recent trend in the acquisition of eye fundus images is the usage of smartphones to acquire images.
 OBJECTIVES: This paper focuses on the study of existing works which incorporated smartphones for obtaining fundus images and various devices available in the market. Also, the common datasets used for carrying out DR detection using smartphone-based fundus images as well as the classification models used for the diagnosis of DR are explored.
 METHODS: A search of information was carried out on articles based on DR detection from fundus images published in the state-of-the-art literatures.
 RESULTS: Majority of the works uses SBFI devices like 20D lens, EyeExaminer etc. to obtain fundus image. The common databases used for the study are EyePACS, Messidor, etc. and the classification models mostly rely on deep learning frameworks.
 CONCLUSION: The use of smartphones for capturing fundus images for DR detection are explored. Smartphone devices, datasets used for the study and currently available classification models for SBFI based DR detection are discussed in detail. This paper portrays various approaches currently being employed in SBFI based DR detection.

Diabetic retinopathy, a condition resulting from prolonged high blood sugar levels that damage the retina, can cause vision impairment and, if untreated, lead to blindness. With advances in medical imaging and the availability of fundus image collections such as Madrid Messidor and DRIVE, computer-aided diagnosis (CAD) systems have become instrumental in identifying and categorizing cases. Machine learning, a branch of artificial intelligence, has demonstrated remarkable success in medical image processing, showing great potential for the early detection of diabetic retinopathy—a condition often challenging to diagnose in its early stages due to a lack of symptoms. This review examines prior studies leveraging machine learning algorithms, such as convolutional neural networks (CNNs), support vector machines (SVMs), and k-nearest neighbors (KNN), for diabetic retinopathy detection using fundus image datasets. It also explores existing challenges, including dataset variability, computational demands, and the generalizability of models across diverse populations. Highlighting methodologies, datasets, and performance metrics like accuracy, sensitivity, and specificity, this article aims to provide a cohesive understanding of the current landscape, delineate strengths and limitations, and suggest directions for future research.

Diabetic Retinopathy (DR) is a microangiopathic complication of diabetes mellitus that can cause visual impairment to permanent blindness. Early detection of DR is essential to prevent disease progression, but conventional methods require time, cost, and expertise that are not always available. This study aims to compare the performance of the Random Forest (RF) and Support Vector Machine (SVM) algorithms in DR classification based on texture features extracted from retinal fundus images. The dataset used consists of 3,000 retinal fundus images obtained from the Kaggle platform, divided into 2,400 training data and 600 test data. Image preprocessing includes conversion to grayscale, resizing to a resolution of 128×128 pixels, and normalization. Feature extraction is performed using a combination of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) to produce a 14-dimensional feature vector. Performance evaluation uses accuracy, precision, recall, F1-score, ROC curve, and 5-fold cross-validation metrics. The results showed that Random Forest significantly outperformed SVM with an accuracy of 96% compared to 64%, an AUC value of 0.99 compared to 0.72, and an average cross-validation accuracy of 94.5% compared to 63.42%. Random Forest also showed balanced performance in both classes with precision, recall, and F1-score of 0.96, while SVM experienced classification imbalance especially in the disease class. This study proves that Random Forest is a more optimal algorithm for an automatic DR detection system based on fundus image texture features and can support increasing the accessibility of DR screening in areas with limited specialist medical personnel.

High blood glucose levels cause lesions on the retina of the eye, resulting in a degenerative condition known as diabetic retinopathy (DR), which impacts vision and can cause irreversible vision loss. The most common cause of blindness in diabetic people is thought to be diabetic retinopathy. Early diagnosis of diabetic retinopathy is essential to efficiently maintaining the patient’s vision. We attempted to give first-hand verification to this fundamental problem of DR detection to save time, money and efforts of ophthalmologists. The latter also proved to be more challenging, especially early on in the disease, when disease characteristics are less obvious in the fundus images. Deep learning algorithms and machine learning-based medical image analysis have aided in the early identification of diabetic retinopathy along with the evaluation of retinal fundus images. This paper attempts to preprocess and binary classify fundus images from the famous Aptos dataset using finetuned ResNet50 as well as features extraction from ResNet50 and later classifying using machine learning models. We have achieved an accuracy of 0.9802, an AUC score of 0.9937, F1 score of 0.9870, a precision of 0.9890, a recall as 0.9845 and kappa score of 0.9481 on the evaluation data by fine-tuning of ResNet50.

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.

To study the effectiveness of two digital 50 degree photographic fields per eye, stored compressed or integrally, in the grading of diabetic retinopathy, in comparison to 35-mm colour slides. Two-field digital non-stereoscopic retinal photographs and two-field 35-mm retinal photographs were made at the same time from patients visiting a diabetic retinopathy outpatient clinic. The digital images were stored integrally (TIFF-file) and in a compressed way (JPEG-file). Two ophthalmologists assessed the photographs in a masked fashion. The results were compared. The sensitivity and specificity for the detection of vision-threatening diabetic retinopathy were calculated, using only the grading of the most affected eye. The differences between the retinopathy gradings of the two kinds of photographs were analysed. The agreement for the grading of DR compared to slides was good, both for the compressed and for the integrally stored images (kappa 0.63-0.68). The sensitivity for the detection of vision-threatening diabetic retinopathy using the JPEG-stored images was 0.72-0.74, specificity 0.93-0.98. The sensitivity for vision-threatening retinopathy detection using the integrally stored images was 0.86-0.92, specificity 0.93. Two-field digital retinal photography is effective in diabetic retinopathy grading and it can replace 35-mm retinal photography. Vision-threatening retinopathy can be detected on the images with reasonable to good sensitivity and specificity. An experienced grader should assess the images. The compression of the digital images seems to have some adverse effect on the detection of diabetic retinopathy.

Diabetic Retinopathy (DR) and Glaucoma are the ocular diseases that are main causes of vision loss. DR and glaucoma are asymptomatic in nature. Early detection can help to reduce disease-related vision loss. Manual method of detecting these diseases is time consuming, expensive and requires skilled supervision. Factors such as poor contrast of fundus images, disease-specific segmentation approach and anatomical factors may all lead to inaccuracies in segmentation-based approach for localizing landmarks. Automated diagnosis of DR and glaucoma can overcome the shortcomings of manual method and reduce the burden on ophthalmologists during mass screening. This work proposes an automated framework for detection of DR and glaucoma using non-linear features that include Higher Order Spectra (HOS), various types of entropies (Kapur entropy, Renyi entropy, Yager entropy and Shannon entropy) and Fractal Dimension (FD). These non-linear features are capable of capturing minute pixel variations in fundus images for classification of normal, DR or glaucoma. For classification, Support Vector Machine (SVM) classifier with different kernels was used. Results shows that SVM-Radial Basis Function (RBF) kernel combination resulted in maximum accuracy of 85%, sensitivity of 84% and specificity of 94.32%. Based on the results it shows that the three-class classification of normal, DR and glaucoma using non-linear feature analysis and SVM can be useful for mass screening.

Diabetes, referred to as diabetes mellitus, describes a group of metabolic diseases in which the person has high blood glucose. Possible complications that can be caused by badly controlled diabetes: Eye complications, Foot complication, Skin complications, Heart problems, Hypertension, etc. Diabetic retinopathy (DR), a common complication of diabetes, affects the blood vessels in the retina. It is due to the retina not receiving enough oxygen. In this work, publically available MESSIDOR database with 1200 fundus images are considered. Due to the textural changes in the retinal fundus images texture analysis methods like statistical moments and GLCM are used and extracted 40 features. The unbalanced dataset decreases the accuracy so oversampling is done before classification. Classifiers such as Support Vector Machine (SVM), Random Forests, Gradient boost, AdaBoost, Gaussian Naive Bayes used to detect the DR. Each algorithm has its own advantages and varying accuracy, SVM compared to others have good accuracy of 88.71%, Random forests technique accuracy of 83.34%, Gradient boost algorithm accuracy of 83.34%, while AdaBoost and Gaussian Naive Bayes methods reached accuracy of 54.3% and 37.09% respectively.

ABSTRACTThe early detection of diabetic retinopathy (DR) illnesses improves diagnosis and lowers the risk of permanent blindness. As a result, screening for DR in fundus images is an important method used to diagnose diabetes and other eye diseases. However, detecting diseases manually requires a significant amount of time and work. Deep learning (DL) techniques have produced encouraging results in categorizing fundus images. Still, the multi‐class DR disease remains a difficult task. Thus, the proposed framework adopted a novel Criss‐Cross Attention‐Based Squeeze‐and‐Excitation Assisted Vision Transformer (CCA‐SE‐ViT) model to classify DR from fundus images. Initially, the defective region of the retina is segmented using a novel dilated depth‐wise separable convolutional U‐Net model (dDSC‐UNet). Then, using the segmented regions, the fundus images are classified into multiple classes as age‐related macular degeneration (AMD), DR, glaucoma, cataracts, myopia, hypertension, normal, other abnormalities, and DR cases are classified into no DR, mild, moderate, severe, and proliferative DR, respectively. The retinal fundus images are obtained from publicly available datasets like OIA‐ODIR and APTOS 2019. The proposed methodology for multi‐class categorization of retinal illnesses in the OIA‐ODIR dataset yielded 97.2% accuracy, 96.7% precision, 96.1% recall, 95.9% F1‐score, and 96.4% specificity. The APTOS dataset was used for multi‐class classification of DR illnesses, and the results were 99.68% accuracy, 99.08% precision, 99.31% recall, 99.19% F1‐score, and 99.26% specificity. The results demonstrated that the proposed method accurately identifies DR using retinal fundus images.

Diabetic Retinopathy (DR) could be a mortal eye ailment that happens in people who have the disease named diabetics which hurts mainly on retina and after a long duration, it may lead to visual lacking. Diabetic Retinopathy Detection (DRD) through the integration of state of the art Profound Proficiency styles. This research used dataset, which was obtained from Eye Foundation Hospital Bangalore and Narayana Netralaya Bangalore, In this paper authors designed the frameworks within the field of profound Convolutional Neural Networks (CNNs), which have demonstrated progressive changes in numerous areas of computer vision counting therapeutic imaging, and researchers bring their control to the conclusion of eye fundus images. This proposed outline is combination of three stages. To begin with, the fundus picture is pre-processed utilizing an intensity of normalised procedure and augmented method. 2nd, the pre-processed picture is input to distinctive foundations of the CNN architecture in arrange to extricate a point vector for the evaluating process. 3rd, a classification is utilized for DRD and decides its review (e.g., no DR, mild, severe, moderate, or Proliferative Diabetic Retinopa-thy). A trained model with Resnet50, Inception V3, VGG-19, DenseNet-121 and MobileNetV2 architectures will extricate the Indus images of the eye. The outcome is coming with amazing exactness of 93.79 percentile, which is better by 7% than earlier work, by utilizing several activation functions in the new DiabRetNet architecture.

BackgroundWith the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages.MethodsThis is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19,904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented.ResultsThe sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19, 83.18, 88.64, 89.59, and 85.02%. The specificity are 63.07, 70.96, 64.16, 70.38, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity.ConclusionsSmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading.

To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain adaptation (SFDA) method for efficient and effective DR identification from unlabeled data. A multi-SFDA method was proposed for DR identification. This method integrates multiple source models, which are trained from the same source domain, to generate synthetic pseudo labels for the unlabeled target domain. Besides, a softmax-consistence minimization term is utilized to minimize the intra-class distances between the source and target domains and maximize the inter-class distances. Validation is performed using three color fundus photograph datasets (APTOS2019, DDR, and EyePACS). The proposed model was evaluated and provided promising results with respectively 0.8917 and 0.9795 F1-scores on referable and normal/abnormal DR identification tasks. It demonstrated effective DR identification through minimizing intra-class distances and maximizing inter-class distances between source and target domains. The multi-SFDA method provides an effective approach to overcome the challenges in DR identification. The method not only addresses difficulties in data labeling and privacy issues, but also reduces the need for large amounts of labeled data required by deep learning methods, making it a practical tool for early detection and preservation of vision in diabetic patients.

Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness worldwide, and early detection with precise severity classification is critical to reduce vision loss.Retinal fundus imaging is the most widely used modality for DR screening, but manual diagnosis is time-consuming, subjective, and prone to variability.Existing deep learning methods often suffer from noise sensitivity, overfitting, and limited ability to classify across all severity levels, which reduces their clinical applicability in large-scale screening.To address these limitations, this work is motivated by the need for an automated, accurate, and robust DR detection framework that can effectively support ophthalmologists in timely intervention.The novelty of this study lies in the development of a Fuzzy-Embedded Recurrent Neural Network (FERNN) combined with a Bilinear Double-Order Filter (BDOF).The BDOF enhances fundus image clarity by suppressing noise while preserving fine retinal details, and FERNN integrates fuzzy logic with recurrent learning to manage uncertainty and capture sequential dependencies in retinal features capabilities not achieved by conventional CNN or hybrid models.Using the Indian Diabetic Retinopathy Image Database (IDRiD), the proposed framework classifies DR into five clinically significant stages, from mild non-proliferative DR to proliferative DR.Experimental results demonstrate that FERNN achieves 89.20% accuracy and 85.44% precision, outperforming advanced baselines such as hybrid Inception-ResNet, DCGAN, and graph neural network models by up to 30.29%.These findings confirm that the proposed FERNN-BDOF framework provides a novel, robust, and scalable solution for automated DR detection, with strong potential for real-world clinical deployment.