Detection Of Diabetic Retinopathy Research Articles

Deep Learning-Based Analysis for Diabetic Retinopathy Identification

The eye condition known as diabetic retinopathy (DR) is characterized by damage to the blood vessels in the retina. Blindness may result if it is not identified in a timely manner. Early detection and treatment of DR can greatly lower the risk of visual loss. Experts with a great deal of training often use colored fundus photos to diagnose this terrible disease. Compared to computer-aided methods, manual diagnosis of DR retina fundus images by ophthalmologists takes longer because of the rising number of diabetic patients worldwide. Consequently, automatic DR detection is becoming essential. With an emphasis on medical research, deep neural network applications in healthcare have advanced significantly. The goal of this effort is to identify the five stages of DR: Normal, Mild, Moderate, Severe, and Proliferate_DR. Deep learning is one of the most popular methods for improving performance, particularly in the categorization and interpretation of medical images. Six deep-learning models—Custom CNN, Resnet50, Densenet121, EfficientNetB0, EfficientNetB2, and ViT—for the acceleration of diabetic retinopathy (DR) detection were evaluated using an extensive fundus image dataset that we got from Kaggle. With enhanced accuracy of 89%, precision of 89%, recall of 89%, and F1-score of 89% in a five-stage DR classification, the results show the superior performance of a DenseNet121 model.

Geometric Self-Supervised Learning: A Novel AI Approach Towards Quantitative and Explainable Diabetic Retinopathy Detection

Background: Diabetic retinopathy (DR) is the leading cause of blindness among working-age adults. Early detection is crucial to reducing DR-related vision loss risk but is fraught with challenges. Manual detection is labor-intensive and often misses tiny DR lesions, necessitating automated detection. Objective: We aimed to develop and validate an annotation-free deep learning strategy for the automatic detection of exudates and bleeding spots on color fundus photography (CFP) images and ultrawide field (UWF) retinal images. Materials and Methods: Three cohorts were created: two CFP cohorts (Kaggle-CFP and E-Ophtha) and one UWF cohort. Kaggle-CFP was used for algorithm development, while E-Ophtha, with manually annotated DR-related lesions, served as the independent test set. For additional independent testing, 50 DR-positive cases from both the Kaggle-CFP and UWF cohorts were manually outlined for bleeding and exudate spots. The remaining cases were used for algorithm training. A multiscale contrast-based shape descriptor transformed DR-verified retinal images into contrast fields. High-contrast regions were identified, and local image patches from abnormal and normal areas were extracted to train a U-Net model. Model performance was evaluated using sensitivity and false positive rates based on manual annotations in the independent test sets. Results: Our trained model on the independent CFP cohort achieved high sensitivities for detecting and segmenting DR lesions: microaneurysms (91.5%, 9.04 false positives per image), hemorrhages (92.6%, 2.26 false positives per image), hard exudates (92.3%, 7.72 false positives per image), and soft exudates (90.7%, 0.18 false positives per image). For UWF images, the model’s performance varied by lesion size. Bleeding detection sensitivity increased with lesion size, from 41.9% (6.48 false positives per image) for the smallest spots to 93.4% (5.80 false positives per image) for the largest. Exudate detection showed high sensitivity across all sizes, ranging from 86.9% (24.94 false positives per image) to 96.2% (6.40 false positives per image), though false positive rates were higher for smaller lesions. Conclusions: Our experiments demonstrate the feasibility of training a deep learning neural network for detecting and segmenting DR-related lesions without relying on their manual annotations.

Detecting Diabetic Retinopathy Using Machine Learning Algorithms: A Review

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.

An Enhanced Convolutional Neural Network (CNN) based P-EDR Mechanism for Diagnosis of Diabetic Retinopathy (DR) using Machine Learning

This study focuses on Diabetic Retinopathy (DR), a disease caused by diabetes that affects the retina of the eye and eventually leads to blindness. Diabetes development progresses to retinopathy and must be addressed at an early stage for effective treatment. Currently, DR is classified as Non-Proliferative DR (NPDR) and Proliferative DR (PDR). This study proposes an Enhanced DR (P-EDR) method based on CNN using a high-resolution dataset benchmark of retinal images. Initially, the data were preprocessed by normalization, augmentation, and resizing to improve image quality and feature extraction. Evaluation was based on accuracy, specificity, sensitivity, and AUC-ROC. The proposed CNN-based P-EDR outperformed advanced ML strategies such as Support Vector Machine (SVM), Random Forest (RF), Probabilistic Neural network (PNN), and Gradient Boosting Machine (GBM) that were executed and compared to diagnose and classify DR. The proposed P-EDR extracts features such as a hemorrhage of the NPDR retina image to identify the disease using image processing for classification. P-EDR provides significant features from images in detection and classification, making it a successful model for diagnosing DR with improved accuracy of 93%, sensitivity of 92%, specificity of 94%, and AUC-ROC of 0.97%. These results highlight the potential of a P-EDR-based machine learning model to support ophthalmologists with the early and precise detection of DR, eventually helping with appropriate treatment and prevention of vision loss.

An efficient automatic diabetic retinopathy grading using a two-way cascaded convolution neural network

High blood sugar levels lead to an eye disease called diabetic retinopathy. This disease causes vision loss from adults to children. Early detection and proper treatment can reduce vision loss. This research suggests computer-aided diagnosis-based early detection of diabetic retinopathy. The main goal of this study is to automatically detect non-proliferative diabetic retinopathy in any retinal imaging. The proposed model consists of two main stages namely, pre-processing and classification. The first stage is to collect the images from the dataset, after which they are pre-processed using the techniques of image enhancement, noise removal, blurring effects, etc. For classification, a two-way cascaded convolution neural network is developed. To improve the effectiveness of the classifier, the handcrafted features are extracted from the image and fused with the proposed classifier. The suggested system divides images of diabetic retinopathy into four categories such as none, mild, moderate, and severe diabetic retinopathy. The effectiveness of the suggested technique is evaluated using a variety of criteria. The diagnostic efficacy of the proposed model is demonstrated through a comparative analysis with state-of-the-art methodologies, showcasing its performance against established approaches.

Automated detection of diabetic retinopathy using an improved deep learning model with smartphone images

Automated detection of diabetic retinopathy using an improved deep learning model with smartphone images

Visual impairment prevention by early detection of diabetic retinopathy based on stacked auto-encoder

Diabetic retinopathy (DR) presents a significant concern among diabetic patients, often leading to vision impairment or blindness if left untreated. Traditional diagnosis methods are prone to human error, necessitating accurate alternatives. While various computer-aided systems have been developed to assist in DR detection, there remains a need for accurate and efficient methods to classify its stages. In this study, we propose a novel approach utilizing enhanced stacked auto-encoders for the detection and classification of DR stages. The classification is performed across one healthy (normal) stage and four DR stages: mild, moderate, severe, and proliferative. Unlike traditional CNN approaches, our method offers improved reliability by reducing time complexity, minimizing errors, and enhancing noise reduction. Leveraging a comprehensive dataset from KAGGLE containing 35,126 retinal fundus images representing one healthy (normal) stage and four DR stages, our proposed model demonstrates superior accuracy compared to existing deep learning algorithms. Data augmentation techniques address class imbalance, while SAEs facilitate accurate classification through layer-wise unsupervised pre-training and supervised fine-tuning. We evaluate our model’s performance using rigorous quantitative measures, including accuracy, recall, precision, and F1-score, highlighting its effectiveness in early disease diagnosis and prevention of blindness. Experimental results across different training/testing ratios (50:50, 60:40, 70:30, and 75:25) showcase the model’s robustness. The highest accuracy achieved during training was 93%, while testing accuracy reached 88% on a training/testing ratio of 75:25. Comparative analysis underscores the model’s superiority over existing methods, positioning it as a promising tool for early-stage DR detection and blindness prevention.

Deep learning model for automatic detection of different types of microaneurysms in diabetic retinopathy.

This study aims to develop a deep-learning-based software capable of detecting and differentiating microaneurysms (MAs) as hyporeflective or hyperreflective on structural optical coherence tomography (OCT) images in patients with non-proliferative diabetic retinopathy (NPDR). A retrospective cohort of 249 patients (498 eyes) diagnosed with NPDR was analysed. Structural OCT scans were obtained using the Heidelberg Spectralis HRA + OCT device. Manual segmentation of MAs was performed by five masked readers, with an expert grader ensuring consistent labeling. Two deep learning models, YOLO (You Only Look Once) and DETR (DEtection TRansformer), were trained using the annotated OCT images. Detection and classification performance were evaluated using the area under the receiver operating characteristic (ROC) curves. The YOLO model performed poorly with an AUC of 0.35 for overall MA detection, with AUCs of 0.33 and 0.24 for hyperreflective and hyporeflective MAs, respectively. The DETR model had an AUC of 0.86 for overall MA detection, but AUCs of 0.71 and 0.84 for hyperreflective and hyporeflective MAs, respectively. Post-hoc review revealed that discrepancies between automated and manual grading were often due to the automated method's selection of normal retinal vessels. The choice of deep learning model is critical to achieving accuracy in detecting and classifying MAs in structural OCT images. An automated approach may assist clinicians in the early detection and monitoring of diabetic retinopathy, potentially improving patient outcomes.

Diabetic Detection from Images of the Eye

This cross-sectional study aims to detect Diabetic Retinopathy (DR) in patients who have had retinal scans and ophthalmological exams. The research makes use of tailored retinal images together with the OPF (Optimum-Path Forest) and RBM (Restricted Boltzmann Machine) models to categorize images according to the presence or absence of DR. In this work, features were extracted from the retinal images using both the RBM and OPF models. In particular, after a thorough system training phase, RBM was able to extract between 500 and 1000 features from the images. The study included fifteen distinct trial series, each with thirty cycles of repetition. The research comprised 122 eyes, or 73 diabetic patients, with a gender distribution that was reasonably balanced and an average age of 59.7 years. Remarkably, the RBM-1000 model stood out as the top performer, with the highest overall accuracy of 89.47% in diagnosis. In terms of specificity, the RBM-1000 and OPF-1000 models surpassed the competition, correctly categorizing all images free of DR symptoms. These findings highlight the potential of machine learning, particularly the RBM model, for self-identifying illnesses. The potential of machine learning models—in particular, RBM and OPF—to automate the diagnosis of diabetic retinopathy is demonstrated by this work. The results show how well the RBM model diagnoses, how sensitive it is, and how well it can be applied for efficient DR screening and diagnosis. This information may be used to improve the effectiveness of systems that identify retinal illnesses

Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space on Fundus Imaging

Diabetic retinopathy (DR) is an eye disorder triggered by diabetes that might result in loss of sight. Earlier diagnosis of DR is critical since it might cause loss of sight. Manual diagnoses of DR severity by ophthalmologists are time-consuming and challenging. As a result, there has been considerable attention on designing an automatic technique for DR detection using fundus photographs. In medical science, prognosis and diagnosis are the most challenging tasks due to the presence of fuzziness in medical images and the restricted subjectivity of the experts. Neutrosophic Set (NS) in medical image analysis provides an understanding of the NS concepts, together with knowledge of how to collect, handle, interpret, and analyze clinical images using NS techniques. The neutrosophic set (NS), which is a generality of fuzzy set, provides the overcoming prospect of the restriction of fuzzy-based models for the analysis of medical images. This manuscript develops a Robust Diabetic Retinopathy Detection and Grading using Neutrosophic Topological Vector Space (DRDG-NSTVS) technique on fundus images. The DRDG-NSTVS technique begins with Median Filter (MF) noise removal to optimize the clarity of fundus photographs by successfully eliminating noises. Later, the InceptionV3 is used to perform feature extraction for identifying complicated features and patterns related to DR. The parameter tuning is performed by the moth flame optimization (MFO) technique to ensure superior performance of the model. The final diagnoses and classification of DR are accomplished utilizing the NSTVS classifiers that easily perform the uncertainties inherent in medicinal statistics. The simulation was conducted on a benchmark dataset to examine the proposed model performance. This combined method gives a greatly reliable and accurate solution for the earlier diagnosis and detection of DR

Multi-Label Diabetic Retinopathy Detection Using Transfer Learning Based Convolutional Neural Network

Retinopathy is a progressive and common retinal disease that most progressive diabetics suffer from and causes blood vessels in the retina to swell and leak blood and fluid. This condition requires timely diagnosis via medical experts to prevent causing visual loss among patients. To enhance the feasibility of checking many persons, diverse deep-learning schemes have recently been developed for diabetic retinopathy detection. In this paper, retinopathy image detection system based on diverse deep learning schemes (VGG-19, DenseNet-121, and EfficientNet-B6) has been presented. The implemented deep learning schemes with multi-label classification are trained and tested using the Asia Pacific Tele Ophthalmology Society (APTOS-2019) dataset, and the two combined datasets Indian Diabetic Retinopathy Image Dataset (IDRiD) and Messidor-2. The system outcomes of classification are exhibited as sensitivity, precision, F1Score, and accuracy measurements, and the system performance is compared with recently existing related systems. The attained outcomes indicate that the implemented EfficientNetB6 network outperforms peers’ schemes and related systems via realizing supreme accuracy using balanced multi-class retinopathy datasets.

Automatic Detection and Classification of Diabetic Retinopathy from Optical Coherence Tomography Angiography Images using Deep Learning - A Review

Automatic Detection and Classification of Diabetic Retinopathy from Optical Coherence Tomography Angiography Images using Deep Learning - A Review

Quantifying the Characteristics of Diabetic Retinopathy in Macular Optical Coherence Tomography Angiography Images: A Few-Shot Learning and Explainable Artificial Intelligence Approach.

Early detection and accurate staging of diabetic retinopathy (DR) are important to prevent vision loss. Optical coherence tomography angiography (OCTA) images provide detailed insights into the retinal vasculature, revealing intricate changes that occur as DR progresses. However, interpreting these complex images requires significant expertise and is often time-intensive. Deep learning techniques have the potential to automate DR analysis. However, they typically require large datasets for effective training. To address the challenge of limited data in this emerging imaging field, a combined approach using few-shot learning (FSL) and self-attention mechanisms within explainable AI (XAI) was explored. To investigate and evaluate the potential of an FSL-self-attention XAI approach to improve the accuracy of DR staging classification using OCTA images. A total of 206 OCTA images, comprising 104 non-proliferative diabetic retinopathy (NPDR) and 102 proliferative diabetic retinopathy (PDR) cases, were analyzed using the FSL method. Three pre-trained networks (ResNet-50, DenseNet-161, and MobileNet-v2) were employed, with the top-performing model subsequently integrated with the Match-Them-Up Network (MTUNet) to provide explainable interpretations using a self-attention mechanism. The performance of the models was evaluated by applying standard metrics, including accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). The performance of the MTUNet model is assessed by calculating pattern-matching scores for PDR and NPDR classes. The ResNet-50 pre-trained model in FSL demonstrated the best overall performance, achieving an accuracy of 76.17%, a sensitivity of 81.83%, a specificity of 70.5%, and 0.82 AUC in classifying DR stages. MTUNet provided pattern-matching scores of 0.77 and 0.75 for PDR and NPDR classes, respectively. FSL and self-attention mechanisms in XAI offer promising approaches for accurate DR stage classification, especially in data-limited scenarios. This could potentially facilitate early DR detection and inform clinical decision-making.

A Novel Approach for Early Detection and Grading of Diabetic Retinopathy by using Ensemble Model

A Novel Approach for Early Detection and Grading of Diabetic Retinopathy by using Ensemble Model

Convolutional neural networks for diabetic retinopathy detection

Convolutional neural networks for diabetic retinopathy detection

The Relationship of Serum Diabetes Antibodies With the Development of Early Diabetic Retinopathy Findings in Children With Type 1 Diabetes Mellitus

Purpose To explore how serum diabetes autoantibodies are related to the development of early diabetic retinopathy in children with type 1 diabetes mellitus. Methods In this prospective and observational study, 62 patients with type 1 diabetes mellitus who had not yet developed clinical diabetic retinopathy were followed up for at least 5 years. Healthy volunteers aged 10 to 20 years were also included. Insulin, pancreatic islet cells, and glutamic acid decarboxylase (GAD) autoantibodies were measured with an RIA kit at the time of type 1 diabetes mellitus diagnosis. Optical coherence tomography angiography (OCTA) was used to evaluate the foveal avascular zone (FAZ) and parafoveal vascular density (PVD) for the development of early diabetic retinopathy among the groups. Patients' OCTA findings were compared with those of healthy volunteers. The obtained data were analyzed via IBM SPSS Statistics for Windows, version 27.0. Spearman's rank correlation test and regression analysis were performed to determine independent predictors of OCTA and type 1 diabetes mellitus parameters. Results Eighteen boys and 44 girls with type 1 diabetes mellitus with a median age of 15.6 years (range: 10.08 to 20.88 years) were evaluated. Healthy control participants with a median age of 15.3 years (range: 14.2 to 18.2 years) were also included. The mean FAZ was greater in the type 1 diabetes mellitus group than in the healthy control group ( P = .013 and .119, respectively). The mean PVD was significantly lower in the type 1 diabetes mellitus group than in the healthy control group. There was no significant correlation between serum diabetes autoantibodies (GAD and insulin autoantibodies) and FAZ or PVD (FAZ and GAD; r = 0.138, P = .286, FAZ and anti-insulin; r = 0.100, P = .441, PVD and GAD; r = −0.151, P = .24, PVD and anti-insulin; r = −0.087, P = .499). Conclusions Type 1 diabetes mellitus in children without clinically detectable diabetic retinopathy is associated with impaired retinal microcirculation and irregularities at the FAZ margin. Impaired retinal microcirculation and irregularities were associated with glycated hemoglobin levels in the study group. Thus, studies with larger patient series are needed. [ J Pediatr Ophthalmol Strabismus . 20XX;X(X):XXX–XXX.]

Artificial Intelligence, Cybersight Detection of Diabetic Retinopathy in the Elderly in Vietnam

Diabetic retinopathy (DR) is a highly prevalent cause of vision loss worldwide. Detection of DR requires substantial human resources and high medical costs. Therefore, the use of diagnostic software has been recently explored. The study aimed to assess the results of DR diagnoses by Cybersight, an artificial intelligence software. A total of 1,012 patients with type 2 diabetes mellitus (1,943 eyes) with a mean age of 74.61 ± 6.73 years were included. Comprehensive demographic and clinical data were gathered, and all patients underwent color fundus photography following Cybersight's standardized protocols. The study compared Cybersight's accuracy with that of ophthalmologists in identifying key DR lesions, including retinal microvascular changes, exudates, hemorrhages, the diagnosis and staging of DR, using sensitivity, specificity, and weighted Kappa metrics. The prevalence of DR was 16.2%. A high level of agreement was found between Cybersight and ophthalmologists in DR diagnosis, with a sensitivity of 85.0%, specificity of 95.8%, and a weighted Kappa of 0.78. The presence of cataracts and the degree of pupil dilation notably impacted on the accuracy of DR diagnosis. The results have important implications for the potential application of Cybersight as a low-cost and effective tool for diabetic eye screening.

Enhancing diabetic retinopathy and macular edema detection through multi scale feature fusion using deep learning model.

This work tackles the growing problem of early identification of diabetic retinopathy and diabetic macular edema. The deep neural network design utilizes multi-scale feature fusion to improve automated diagnostic accuracy. Methods This approach uses convolutional neural networks (CNN) and is designed to combine higher-level semantic inputs with low-level textural characteristics. The contextual and localized abstract representations that complement each other are combined via a unique fusion technique. Use the MESSIDOR dataset, which comprisesretinal images labeled with pathological annotations, for model training and validation toensure robust algorithm development. The suggested model shows a 98% general precision and good performance in diabetic retinopathy. This model achieves an impressive nearly 100% exactness for diabetic macular edema, with particularly high accuracy (0.99). Consistent performance increases the likelihood that the vision will be upheld through public screening and extensive clinical integration.

Automated Detection of Diabetic Retinopathy: A Comparative Study of Machine Learning Algorithms

Automated Detection of Diabetic Retinopathy: A Comparative Study of Machine Learning Algorithms

Evaluating the efficacy of AI systems in diabetic retinopathy detection: A comparative analysis of Mona DR and IDx-DR.

To compare two artificial intelligence (AI)-based Automated Diabetic Retinopathy Image Assessment (ARIA) softwares in terms of concordance with specialist human graders and referable diabetic retinopathy (DR) diagnostic capacity. Retrospective comparative study including 750 consecutive diabetes mellitus patients imaged for non-mydriatic fundus photographs. For each patient four images (45 degrees field of view) were captured, centered on the optic disc and macula. Images were manually graded for severity of DR as no DR, any DR (mild non-proliferative diabetic retinopathy [NPDR] or more), referable DR (RDR (more than mild DR)), or sight-threatening DR (severe NPDR or more severe disease and/or clinically significant diabetic macular edema [CSDME]). IDx-DR and MONA DR output was compared with manual grading and with each other. Total sample size was 750 patients, of which 55 were excluded due to ungradable images. Out of the remaining 695 patients 522 (75%) were considered as having no DR by manual consensus grading, and 106 (15%) as having RDR. Agreement between raters varied between moderate to substantial. IDx-DR showed moderate agreement with human grading (k = 0.4285) while MONA DR had substantial agreement (k = 0.6797). Out of 106 patients with a ground truth of RDR, IDx-DR identified 105 and MONA DR identified 99. The sensitivity and specificity rates for RDR detection of IDx-DR were 99.1 and 71.5% compared with MONA DR of 93.4 and 89.3% respectively. Of note, both ARIAs had 100% sensitivity for the detection of STDR. Both ARIAs performed well in this study population, both with sensitivity for RDR screening over 90%, with IDx-DR showing higher sensitivity and MONA DR higher specificity. MONA DR showed superior agreement with human certified graders.