CAD-EYE: An Automated System for Multi-Eye Disease Classification Using Feature Fusion with Deep Learning Models and Fluorescence Imaging for Enhanced Interpretability

Background: Diabetic retinopathy, hypertensive retinopathy, glaucoma, and contrast-related eye diseases are well-recognized conditions resulting from high blood pressure, rising blood glucose, and elevated eye pressure. Later-stage symptoms usually include patches of cotton wool, restricted veins in the optic nerve, and buildup of blood in the optic nerve. Severe consequences include damage of the visual nerve, and retinal artery obstruction, and possible blindness may result from these conditions. An early illness diagnosis is made easier by the use of deep learning models and artificial intelligence (AI). Objectives: This study introduces a novel methodology called CAD-EYE for classifying diabetic retinopathy, hypertensive retinopathy, glaucoma, and contrast-related eye issues. Methods: The proposed system combines the features extracted using two deep learning (DL) models (MobileNet and EfficientNet) using feature fusion to increase the diagnostic system efficiency. The system uses fluorescence imaging for increasing accuracy as an image processing algorithm. The algorithm is added to increase the interpretability and explainability of the CAD-EYE system. This algorithm was not used in such an application in the previous literature to the best of the authors' knowledge. The study utilizes datasets sourced from reputable internet platforms to train the proposed system. Results: The system was trained on 65,871 fundus images from the collected datasets, achieving a 98% classification accuracy. A comparative analysis demonstrates that CAD-EYE surpasses cutting-edge models such as ResNet, GoogLeNet, VGGNet, InceptionV3, and Xception in terms of classification accuracy. A state-of-the-art comparison shows the superior performance of the model against previous work in the literature. Conclusions: These findings support the usefulness of CAD-EYE as a diagnosis tool that can help medical professionals diagnose an eye disease. However, this tool will not be replacing optometrists.

Clinical Utility of Deep Learning Assistance for Detecting Various Abnormal Findings in Color Retinal Fundus Images: A Reader Study

Purpose

To evaluate the clinical usefulness of a deep learning-based detection device for multiple abnormal findings on retinal fundus photographs for readers with varying expertise.

Methods

Fourteen ophthalmologists (six residents, eight specialists) assessed 399 fundus images with respect to 12 major ophthalmologic findings, with or without the assistance of a deep learning algorithm, in two separate reading sessions. Sensitivity, specificity, and reading time per image were compared.

Results

With algorithmic assistance, readers significantly improved in sensitivity for all 12 findings (P < 0.05) but tended to be less specific (P < 0.05) for hemorrhage, drusen, membrane, and vascular abnormality, more profoundly so in residents. Sensitivity without algorithmic assistance was significantly lower in residents (23.1%∼75.8%) compared to specialists (55.1%∼97.1%) in nine findings, but it improved to similar levels with algorithmic assistance (67.8%∼99.4% in residents, 83.2%∼99.5% in specialists) with only hemorrhage remaining statistically significantly lower. Variances in sensitivity were significantly reduced for all findings. Reading time per image decreased in images with fewer than three findings per image, more profoundly in residents. When simulated based on images acquired from a health screening center, average reading time was estimated to be reduced by 25.9% (from 16.4 seconds to 12.1 seconds per image) for residents, and by 2.0% (from 9.6 seconds to 9.4 seconds) for specialists.

Conclusions

Deep learning-based computer-assisted detection devices increase sensitivity, reduce inter-reader variance in sensitivity, and reduce reading time in less complicated images.

Translational Relevance

This study evaluated the influence that algorithmic assistance in detecting abnormal findings on retinal fundus photographs has on clinicians, possibly predicting its influence on clinical application.

Clinical indicators for diabetic eyecare delivered by optometrists in Australia: a Delphi study

CLINICAL RELEVANCE

Valid and updated clinical indicators can serve as important tools in assessing and improving eyecare delivery.

BACKGROUND

Indicators for diabetic eyecare in Australia were previously developed from guidelines published before 2013 and then used to assess the appropriateness of care delivery through a nationwide patient record card audit (the iCareTrack study). To reflect emerging evidence and contemporary practice, this study aimed to update clinical indicators for optometric care for people with type 2 diabetes in Australia.

METHODS

Forty-five candidate indicators, including existing iCareTrack and new indicators derived from nine high-quality evidence-based guidelines, were generated. A two-round modified Delphi process where expert panel members rated the impact, acceptability, and feasibility of the indicators on a 9-point scale and voted for inclusion or exclusion of the candidate indicators was used. Consensus on inclusion was reached when the median scores for impact, acceptability, and feasibility were ≥7 and >75% of experts voted for inclusion.

RESULTS

Thirty-two clinical indicators with high acceptability, impact and feasibility ratings (all median scores: 9) were developed. The final indicators were related to history taking (n = 12), physical examination (n = 8), recall period (n = 5), referral (n = 5), and patient education/communication (n = 2). Most (14 of 15) iCareTrack indicators were retained either in the original format or with modifications. New indicators included documenting the type of diabetes, serum lipid level, pregnancy, systemic medications, nephropathy, Indigenous status, general practitioner details, pupil examination, intraocular pressure, optical coherence tomography, diabetic retinopathy grading, recall period for high-risk diabetic patients without retinopathy, referral of high-risk proliferative retinopathy, communication with the general practitioner, and patient education.

CONCLUSION

A set of 32 updated diabetic eyecare clinical indicators was developed based on contemporary evidence and expert consensus. These updated indicators inform the development of programs to assess and enhance the eyecare delivery for people with diabetes in Australia.

Optical coherence tomography and contrast sensitivity in early diabetic retinopathy

PURPOSE

This study used contrast sensitivity (CS) and optical coherence tomography (OCT) to assess the functional and structural alterations of the macula and the optic nerve head (ONH) in diabetic patients with no retinopathy and those with mild nonproliferative diabetic retinopathy (NPDR).

MATERIALS AND METHODS

In this study, 40 eyes of 20 diabetic patients with no diabetic retinopathy (DR), 40 eyes of 20 diabetic patients with mild NPDR, and 36 eyes of 18 healthy individuals were examined. Best-corrected visual acuity (VA) and CS were performed using early treatment DR study charts and the Pelli-Robson chart, respectively. The macula and ONH were evaluated using OCT, which provided data on the entire retina, inner retinal layer, outer retinal layer, retinal nerve fiber layer (RNFL), and the macula zone-ellipsoid zone-retinal pigment epithelium layer.

RESULTS

VA and CS were significantly different between the three groups (P < 0.001). The entire thickness of the retina and the internal thickness of the retina in the 3-6 mm subfields of the macular region, as well as the thickness of the ganglion cell layer + inner plexiform layer (GCL + IPL) and GCL + IPL + RNFLs, differed significantly across the groups (P < 0.013).

CONCLUSION

In diabetic subjects with no retinopathy, the reduced thickness of the GCL + IPLs is possibly indicative of early neurodegenerative changes in the inner retina. Furthermore, in the diabetic groups, a decrease in CS was observed compared to the control group.

Retinal Perfusion Analysis of Children with Diabetes Mellitus Type 1 Using Optical Coherence Tomography Angiography

(1) Background: This study aims to evaluate retinal perfusion by optical coherence tomography angiography (OCTA) in pediatric patients with type 1 diabetes mellitus (T1D) without diabetic retinopathy (DR). (2) Methods: Thirty-one patients affected by T1D were enrolled. All participants were evaluated using OCTA. The foveal avascular zone (FAZ) and superficial and deep macular vessel density (VD) were analyzed. The correlation of these parameters with metabolic factors such as body mass index (BMI), glycated hemoglobin (HbA1c), and the type of insulin therapy (multiple daily injections, MDI vs. continuous subcutaneous insulin infusion, CSII) was determined. (3) Results: None of the OCTA parameters were significantly different between the groups. The patients' HbA1C level did not influence any of the OCTA parameters. The use of MDI tended to reduce the parafoveal and perifoveal deep VD (p = 0.048 and p = 0.021, respectively) compared to CSII. An elevated BMI tended to increase the deep macular (p = 0.005) and perifoveal VD (p = 0.006). (4) Conclusion: VD and FAZ are normal in pubescent children with T1D without signs of DR. Treatment with CSII may be a better choice compared to MDI, as CSII may be protective against retinal microvascular damage. Our results indicate the need for new clinical parameters of glycemic control in addition to HbA1c which could assess the risk of DR.

Economic evaluation for medical artificial intelligence: accuracy vs. cost-effectiveness in a diabetic retinopathy screening case

Artificial intelligence (AI) models have shown great accuracy in health screening. However, for real-world implementation, high accuracy may not guarantee cost-effectiveness. Improving AI's sensitivity finds more high-risk patients but may raise medical costs while increasing specificity reduces unnecessary referrals but may weaken detection capability. To evaluate the trade-off between AI model performance and the long-running cost-effectiveness, we conducted a cost-effectiveness analysis in a nationwide diabetic retinopathy (DR) screening program in China, comprising 251,535 participants with diabetes over 30 years. We tested a validated AI model in 1100 different diagnostic performances (presented as sensitivity/specificity pairs) and modeled annual screening scenarios. The status quo was defined as the scenario with the most accurate AI performance. The incremental cost-effectiveness ratio (ICER) was calculated for other scenarios against the status quo as cost-effectiveness metrics. Compared to the status quo (sensitivity/specificity: 93.3%/87.7%), six scenarios were cost-saving and seven were cost-effective. To achieve cost-saving or cost-effective, the AI model should reach a minimum sensitivity of 88.2% and specificity of 80.4%. The most cost-effective AI model exhibited higher sensitivity (96.3%) and lower specificity (80.4%) than the status quo. In settings with higher DR prevalence and willingness-to-pay levels, the AI needed higher sensitivity for optimal cost-effectiveness. Urban regions and younger patient groups also required higher sensitivity in AI-based screening. In real-world DR screening, the most accurate AI model may not be the most cost-effective. Cost-effectiveness should be independently evaluated, which is most likely to be affected by the AI's sensitivity.

Diabetic Retinopathy: Clinical Features, Risk Factors, and Treatment Options

Diabetic retinopathy is a common complication of diabetes that affects the eyes and can lead to severe vision loss or blindness if left untreated. Chronic hyperglycemia destroys the blood vessels in the retina, resulting in diabetic retinopathy. The damage can lead to leakage of fluid and blood into the retina, causing edema, hemorrhages, and ischemia. A thorough evaluation by an ophthalmologist is necessary to determine the most appropriate course of treatment for each patient with diabetic retinopathy. The article discusses various surgical treatment options for diabetic retinopathy, including vitrectomy, scleral buckling, epiretinal membrane peeling, retinal detachment repair, and the risk factors of diabetic retinopathy. These surgical techniques can help to address the underlying causes of vision loss and prevent further complications from developing or worsening. To avoid complications and maintain vision, this review emphasizes the significance of early detection and treatment of diabetic retinopathy. Patients with diabetic retinopathy can improve their eyesight and quality of life with the help of some surgical treatments. The article also highlights some case studies in the field of diabetic retinopathy.

An advanced deep learning method to detect and classify diabetic retinopathy based on color fundus images

BACKGROUND

In this article, we present a computerized system for the analysis and assessment of diabetic retinopathy (DR) based on retinal fundus photographs. DR is a chronic ophthalmic disease and a major reason for blindness in people with diabetes. Consistent examination and prompt diagnosis are the vital approaches to control DR.

METHODS

With the aim of enhancing the reliability of DR diagnosis, we utilized the deep learning model called You Only Look Once V3 (YOLO V3) to recognize and classify DR from retinal images. The DR was classified into five major stages: normal, mild, moderate, severe, and proliferative. We evaluated the performance of the YOLO V3 algorithm based on color fundus images.

RESULTS

We have achieved high precision and sensitivity on the train and test data for the DR classification and mean average precision (mAP) is calculated on DR lesion detection.

CONCLUSIONS

The results indicate that the suggested model distinguishes all phases of DR and performs better than existing models in terms of accuracy and implementation time.

Predicting of diabetic retinopathy development stages of fundus images using deep learning based on combined features

The number of diabetic retinopathy (DR) patients is increasing every year, and this causes a public health problem. Therefore, regular diagnosis of diabetes patients is necessary to avoid the progression of DR stages to advanced stages that lead to blindness. Manual diagnosis requires effort and expertise and is prone to errors and differing expert diagnoses. Therefore, artificial intelligence techniques help doctors make a proper diagnosis and resolve different opinions. This study developed three approaches, each with two systems, for early diagnosis of DR disease progression. All colour fundus images have been subjected to image enhancement and increasing contrast ROI through filters. All features extracted by the DenseNet-121 and AlexNet (Dense-121 and Alex) were fed to the Principal Component Analysis (PCA) method to select important features and reduce their dimensions. The first approach is to DR image analysis for early prediction of DR disease progression by Artificial Neural Network (ANN) with selected, low-dimensional features of Dense-121 and Alex models. The second approach is to DR image analysis for early prediction of DR disease progression is by integrating important and low-dimensional features of Dense-121 and Alex models before and after PCA. The third approach is to DR image analysis for early prediction of DR disease progression by ANN with the radiomic features. The radiomic features are a combination of the features of the CNN models (Dense-121 and Alex) separately with the handcrafted features extracted by Discrete Wavelet Transform (DWT), Local Binary Pattern (LBP), Fuzzy colour histogram (FCH), and Gray Level Co-occurrence Matrix (GLCM) methods. With the radiomic features of the Alex model and the handcrafted features, ANN reached a sensitivity of 97.92%, an AUC of 99.56%, an accuracy of 99.1%, a specificity of 99.4% and a precision of 99.06%.

MULTI-SCALE DIRECTED ACYCLIC GRAPH-CNN FOR AUTOMATED CLASSIFICATION OF DIABETIC RETINOPATHY FROM OCT IMAGES

Diabetic Retinopathy (DR) is the principal cause of vision loss that interrupts the regular interaction of vascular, neural, and retinal constituents leading to impaired neuronal function and retinal abnormalities. Diagnosis of DR from Optical Coherence Tomography (OCT) image is difficult and time-consuming because several small features must be identified and graded, which results in a strenuous diagnosis when integrated with the complexity of the grading system. This study focuses on classifying DR from normal Spectral Domain-OCT (SD-OCT) images using the Directed Acyclic Graph (DAG) network without any pre-processing techniques. The proposed DAG-CNN model comprises 16 convolutional blocks, which learns multi-scale features automatically from multiple layers in the convolutional network and combines them effectively for the DR and normal prediction. The proposed model is tested on the public OCTID_DR and private LFH_DR SD-OCT databases containing DR and healthy OCT images. The model achieved an accuracy, precision, recall, F1-score, and AUC on OCTID_DR database of 0.9841, 0.9727, 0.9818, 0.9772, and 0.9836, respectively; and on LFH_DR database the respective values are 0.9988, 1, 0.9976, 0.9988, and 0.9988 with only 0.1569 Million of learnable parameters. This method significantly reduces the number of learnable parameters and the model’s computational complexity in terms of memory required and FLoating point OPerations (FLOPs). Guided Gradient-weighted Class Activation Mapping (Grad-CAM) is performed to highlight the regions of SD-OCT images that contribute to the decision of the classifier. Our model significantly surpasses the accuracy of the existing models with lower resource consumption and higher real-time performance.

A New Approach for Detecting Fundus Lesions Using Image Processing and Deep Neural Network Architecture Based on YOLO Model

Diabetic Retinopathy is one of the main causes of vision loss, and in its initial stages, it presents with fundus lesions, such as microaneurysms, hard exudates, hemorrhages, and soft exudates. Computational models capable of detecting these lesions can help in the early diagnosis of the disease and prevent the manifestation of more severe forms of lesions, helping in screening and defining the best form of treatment. However, the detection of these lesions through computerized systems is a challenge due to numerous factors, such as the characteristics of size and shape of the lesions, noise and the contrast of images available in the public datasets of Diabetic Retinopathy, the number of labeled examples of these lesions available in the datasets and the difficulty of deep learning algorithms in detecting very small objects in digital images. Thus, to overcome these problems, this work proposes a new approach based on image processing techniques, data augmentation, transfer learning, and deep neural networks to assist in the medical diagnosis of fundus lesions. The proposed approach was trained, adjusted, and tested using the public DDR and IDRiD Diabetic Retinopathy datasets and implemented in the PyTorch framework based on the YOLOv5 model. The proposed approach reached in the DDR dataset an mAP of 0.2630 for the IoU limit of 0.5 and F1-score of 0.3485 in the validation stage, and an mAP of 0.1540 for the IoU limit of 0.5 and F1-score of 0.2521, in the test stage. The results obtained in the experiments demonstrate that the proposed approach presented superior results to works with the same purpose found in the literature.

Validating automated eye disease screening AI algorithm in community and in-hospital scenarios

Purpose:

To assess the accuracy and robustness of the AI algorithm for detecting referable diabetic retinopathy (RDR), referable macular diseases (RMD), and glaucoma suspect (GCS) from fundus images in community and in-hospital screening scenarios.

Methods

We collected two color fundus image datasets, namely, PUMCH (556 images, 166 subjects, and four camera models) and NSDE (534 images, 134 subjects, and two camera models). The AI algorithm generates the screening report after taking fundus images. The images were labeled as RDR, RMD, GCS, or none of the three by 3 licensed ophthalmologists. The resulting labels were treated as “ground truth” and then were used to compare against the AI screening reports to validate the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of the AI algorithm.

Results

On the PUMCH dataset, regarding the prediction of RDR, the AI algorithm achieved overall results of 0.950 ± 0.058, 0.963 ± 0.024, and 0.954 ± 0.049 on sensitivity, specificity, and AUC, respectively. For RMD, the overall results are 0.919 ± 0.073, 0.929 ± 0.039, and 0.974 ± 0.009. For GCS, the overall results are 0.950 ± 0.059, 0.946 ± 0.016, and 0.976 ± 0.025.

Conclusion

The AI algorithm can work robustly with various fundus camera models and achieve high accuracies for detecting RDR, RMD, and GCS.

Anomaly segmentation in retinal images with poisson-blending data augmentation

Diabetic retinopathy (DR) is one of the most important complications of diabetes. Accurate segmentation of DR lesions is of great importance for the early diagnosis of DR. However, simultaneous segmentation of multi-type DR lesions is technically challenging because of 1) the lack of pixel-level annotations and 2) the large diversity between different types of DR lesions. In this study, first, we propose a novel Poisson-blending data augmentation (PBDA) algorithm to generate synthetic images, which can be easily utilized to expand the existing training data for lesion segmentation. We perform extensive experiments to recognize the important attributes in the PBDA algorithm. We show that position constraints are of great importance and that the synthesis density of one type of lesion has a joint influence on the segmentation of other types of lesions. Second, we propose a convolutional neural network architecture, named DSR-U-Net++ (i.e., DC-SC residual U-Net++), for the simultaneous segmentation of multi-type DR lesions. Ablation studies showed that the mean area under precision recall curve (AUPR) for all four types of lesions increased by >5% with PBDA. The proposed DSR-U-Net++ with PBDA outperformed the state-of-the-art methods by 1.7%-9.9% on the Indian Diabetic Retinopathy Image Dataset (IDRiD) and 67.3% on the e-ophtha dataset with respect to mean AUPR. The developed method would be an efficient tool to generate large-scale task-specific training data for other medical anomaly segmentation tasks.

Deep Red Lesion Classification for Early Screening of Diabetic Retinopathy

Diabetic retinopathy (DR) is an asymptotic and vision-threatening complication among working-age adults. To prevent blindness, a deep convolutional neural network (CNN) based diagnosis can help to classify less-discriminative and small-sized red lesions in early screening of DR patients. However, training deep models with minimal data is a challenging task. Fine-tuning through transfer learning is a useful alternative, but performance degradation, overfitting, and domain adaptation issues further demand architectural amendments to effectively train deep models. Various pre-trained CNNs are fine-tuned on an augmented set of image patches. The best-performing ResNet50 model is modified by introducing reinforced skip connections, a global max-pooling layer, and the sum-of-squared-error loss function. The performance of the modified model (DR-ResNet50) on five public datasets is found to be better than state-of-the-art methods in terms of well-known metrics. The highest scores (0.9851, 0.991, 0.991, 0.991, 0.991, 0.9939, 0.0029, 0.9879, and 0.9879) for sensitivity, specificity, AUC, accuracy, precision, F1-score, false-positive rate, Matthews’s correlation coefficient, and kappa coefficient are obtained within a 95% confidence interval for unseen test instances from e-Ophtha_MA. This high sensitivity and low false-positive rate demonstrate the worth of a proposed framework. It is suitable for early screening due to its performance, simplicity, and robustness.

A Deep Learning Algorithm for Classifying Diabetic Retinopathy Using Optical Coherence Tomography Angiography

Purpose

To develop an automated diabetic retinopathy (DR) staging system using optical coherence tomography angiography (OCTA) images with a convolutional neural network (CNN) and to verify the feasibility of the system.

Methods

In this retrospective cross-sectional study, a total of 918 data sets of 3 × 3 mm² OCTA images and 917 data sets of 6 × 6 mm² OCTA images were obtained from 1118 eyes. A deep CNN and four traditional machine learning models were trained with annotations made by a retinal specialist based on ultra-widefield fluorescein angiography. Separately, the same images of the test data sets were independently graded by two human experts. The results of the CNN algorithm were compared with those of traditional machine learning–based classifiers and human experts.

Results

The proposed CNN achieved an accuracy of 0.728, a sensitivity of 0.675, a specificity of 0.944, an F1 score of 0.683, and a quadratic weighted κ of 0.908 for a six-level staging task, which were far superior to the results of traditional machine learning methods or human experts. The CNN algorithm showed a better performance using 6 × 6 mm² rather than 3 × 3 mm² sized OCTA images and using combined data rather than a separate OCTA layer alone.

Conclusions

CNN-based classification using OCTA images can provide reliable assistance to clinicians for DR classification.

Translational Relevance

This CNN algorithm can guide the clinical decision for invasive angiography or referrals to ophthalmology specialists, helping to create more efficient diagnostic workflow in primary care settings.

Evaluating a Deep Learning Diabetic Retinopathy Grading System Developed on Mydriatic Retinal Images When Applied to Non-Mydriatic Community Screening

Artificial Intelligence has showcased clear capabilities to automatically grade diabetic retinopathy (DR) on mydriatic retinal images captured by clinical experts on fixed table-top retinal cameras within hospital settings. However, in many low- and middle-income countries, screening for DR revolves around minimally trained field workers using handheld non-mydriatic cameras in community settings. This prospective study evaluated the diagnostic accuracy of a deep learning algorithm developed using mydriatic retinal images by the Singapore Eye Research Institute, commercially available as Zeiss VISUHEALTH-AI DR, on images captured by field workers on a Zeiss Visuscout^® 100 non-mydriatic handheld camera from people with diabetes in a house-to-house cross-sectional study across 20 regions in India. A total of 20,489 patient eyes from 11,199 patients were used to evaluate algorithm performance in identifying referable DR, non-referable DR, and gradability. For each category, the algorithm achieved precision values of 29.60 (95% CI 27.40, 31.88), 92.56 (92.13, 92.97), and 58.58 (56.97, 60.19), recall values of 62.69 (59.17, 66.12), 85.65 (85.11, 86.18), and 65.06 (63.40, 66.69), and F-score values of 40.22 (38.25, 42.21), 88.97 (88.62, 89.31), and 61.65 (60.50, 62.80), respectively. Model performance reached 91.22 (90.79, 91.64) sensitivity and 65.06 (63.40, 66.69) specificity at detecting gradability and 72.08 (70.68, 73.46) sensitivity and 85.65 (85.11, 86.18) specificity for the detection of all referable eyes. Algorithm accuracy is dependent on the quality of acquired retinal images, and this is a major limiting step for its global implementation in community non-mydriatic DR screening using handheld cameras. This study highlights the need to develop and train deep learning-based screening tools in such conditions before implementation.

Development of a diabetic retinopathy screening model for a district health system in Limpopo Province, South Africa

Background: Diabetes mellitus (DM) and diabetic retinopathy (DR) are important issues in the district health system (DHS) of South Africa (SA). Guidelines for the management of DR in SA were developed more than a decade ago but not effectively implemented.Aim: The aim of this study was to develop a suitable model for DR that could be effectively implemented by a team of healthcare practitioners (HCPs) to co-manage DM and DR in the DHS of SA.Setting: The study was conducted through Voortrekker District Hospital, Limpopo Province, SA.Methods: A saturated strategy sample study was employed, and questionnaires were distributed to 24 endocrinologists in both private and public practices in Gauteng Province and to three ophthalmologists and 10 medical officers (MOs) in ophthalmology in health institutions in Waterberg and Capricorn districts of Limpopo Province. The questionnaires distributed included questions relating to the recommended roles of primary healthcare (PHC) nurses, MOs in general practice, MOs in ophthalmology, ophthalmic nurses, optometrists, and ophthalmologists to manage patients with DM in the public sector. The Delphi technique was employed requiring experts to comment qualitatively and quantitatively to elicit the required information.Results: At PHC level, PHC nurses are to document a comprehensive patient case history and assess vitals before referring to MOs in general practice. Medical officers in general practice are to assess DM control and screen for target organ disease. All patients with DM are to be referred to optometrists for retinal photography. Optometrists and ophthalmic nurses are to detect, grade and monitor pre-proliferative stages of DR, and refer to MOs in ophthalmology or ophthalmologists at district or tertiary hospitals for surgical intervention or treatment.Conclusion: Based on the expertise of the endocrinologists and ophthalmologists concerned, a DR screening model for a DHS was proposed, reflecting the role of HCPs in the management of DM and DR in the DHS of Limpopo Province, SA.

Systematic review of diabetic eye disease practice guidelines: more applicability, transparency and development rigor are needed

OBJECTIVES

To assess the quality of diabetic eye disease clinical practice guidelines.

STUDY DESIGN AND SETTING

A systematic search of diabetic eye disease guidelines was conducted on six online databases and guideline repositories. Four reviewers independently rated quality using the Appraisal of Guidelines, Research, and Evaluation (AGREE II) instrument. Aggregate scores (%) for six domains and overall quality assessment were calculated. A "good quality" guideline was one with ≥60% score for "rigor of development" and in at least two other domains.

RESULTS

Eighteen guidelines met the inclusion criteria, of which 13 were evidence-based guidelines (involved systematic search and grading of evidence). The median scores (interquartile range (IQR)) for "scope and purpose," "stakeholder involvement," "rigor of development," "clarity of presentation," "applicability" and "editorial independence" were 73.6% (54.2%-80.6%), 48.6% (29.2%-71.5%), 60.2% (30.9%-78.1%), 86.6% (76.7%-94.4%), 28.6% (18.0%-37.8%) and 60.2% (30.9%-78.1%), respectively. The median overall score (out of 7) of all guidelines was 5.1 (IQR: 3.7-5.8). Evidence-based guidelines scored significantly higher compared to expert-consensus guidelines. Half (n = 9) of the guidelines (all evidence-based) were of "good quality."

CONCLUSION

A wide variation in methodological quality exists among diabetic eyecare guidelines, with nine demonstrating "good quality." Future iterations of guidelines could improve by appropriately engaging stakeholders, following a rigorous development process, including support for application in clinical practice and ensuring editorial transparency.

Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study

BACKGROUND

The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable for screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases.

OBJECTIVE

This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images.

METHODS

A generative adversarial network-based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model's performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model's performance were calculated and presented.

RESULTS

Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in 1 external proprietary data set. In the detection of 6 common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR, and myopia were 0.891, 0.916, 0.912, 0.867, 0.895, and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR, and 0.926 for detecting vision-threatening DR.

CONCLUSIONS

The AD approach achieved high sensitivity and specificity in detecting ocular diseases on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening.

An interpretable multiple-instance approach for the detection of referable diabetic retinopathy in fundus images

Diabetic retinopathy (DR) is one of the leading causes of vision loss across the world. Yet despite its wide prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for monitoring their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to retinopathy severity estimates for patients in remote regions or even for complementing the human expert’s diagnosis. Here we propose a machine learning system for the detection of referable diabetic retinopathy in fundus images, which is based on the paradigm of multiple-instance learning. Our method extracts local information independently from multiple rectangular image patches and combines it efficiently through an attention mechanism that focuses on the abnormal regions of the eye (i.e. those that contain DR-induced lesions), thus resulting in a final image representation that is suitable for classification. Furthermore, by leveraging the attention mechanism our algorithm can seamlessly produce informative heatmaps that highlight the regions where the lesions are located. We evaluate our approach on the publicly available Kaggle, Messidor-2 and IDRiD retinal image datasets, in which it exhibits near state-of-the-art classification performance (AUC of 0.961 in Kaggle and 0.976 in Messidor-2), while also producing valid lesion heatmaps (AUPRC of 0.869 in the 81 images of IDRiD that contain pixel-level lesion annotations). Our results suggest that the proposed approach provides an efficient and interpretable solution against the problem of automated diabetic retinopathy grading.

Biomarkers for Progression in Diabetic Retinopathy: Expanding Personalized Medicine through Integration of AI with Electronic Health Records

The goal of personalized diabetes eye care is to accurately predict in real-time the risk of diabetic retinopathy (DR) progression and visual loss. The use of electronic health records (EHR) provides a platform for artificial intelligence (AI) algorithms that predict DR progression to be incorporated into clinical decision-making. By implementing an algorithm on data points from each patient, their risk for retinopathy progression and visual loss can be modeled, allowing them to receive timely treatment. Data can guide algorithms to create models for disease and treatment that may pave the way for more personalized care. Currently, there exist numerous challenges that need to be addressed before reliably building and deploying AI algorithms, including issues with data quality, privacy, intellectual property, and informed consent.

Competency level assessment of healthcare practitioners in managing diabetes and diabetic eye disease in the district health system of Limpopo province, South Africa

Background: There are many gaps in the management of diabetes mellitus (DM) and diabetic eye disease in the district health system (DHS) of South Africa (SA). National guidelines recommend annual eye examinations for patients with DM.Aim: The purpose of this study was to describe the self-reported skill levels of healthcare practitioners (HCPs) to conduct eye examination procedures required for a proposed diabetic retinopathy (DR) screening model.Setting: The study was conducted in public health institutions of Waterberg district and Mankweng Hospital complex (Capricorn district) in Limpopo province, SA.Methods: A cross-sectional design using purposive sampling was conducted, and questionnaires were distributed to a total of 74 HCPs. The questionnaires distributed included questions relating to the competency levels of primary healthcare nurses (PHC nurses), optometrists, ophthalmic nurses and medical officers (MOs) regarding examination procedures in the management of patients with DM and whether they agreed with the developed DR screening model.Results: All the PHC nurses had knowledge about all the examination procedures required in the proposed DR screening model, whilst 94.1% of MOs exhibited knowledge regarding the procedures required from them. Optometrists lacked knowledge of grading DR, and ophthalmic nurses were least knowledgeable about conducting internal and external eye examinations and in detecting and grading DR.Conclusion: The proposed DR screening model did not need modification. The involvement of dieticians and more ophthalmic nurses could be beneficial to the DR screening model.

Evidence Based Prediction and Progression Monitoring on Retinal Images from Three Nations

Purpose

The aim of this work is to demonstrate how a retinal image analysis system, DAPHNE, supports the optimization of diabetic retinopathy (DR) screening programs for grading color fundus photography.

Method

Retinal image sets, graded by trained and certified human graders, were acquired from Saudi Arabia, China, and Kenya. Each image was subsequently analyzed by the DAPHNE automated software. The sensitivity, specificity, and positive and negative predictive values for the detection of referable DR or diabetic macular edema were evaluated, taking human grading or clinical assessment outcomes to be the gold standard. The automated software's ability to identify co-pathology and to correctly label DR lesions was also assessed.

Results

In all three datasets the agreement between the automated software and human grading was between 0.84 to 0.88. Sensitivity did not vary significantly between populations (94.28%–97.1%) with specificity ranging between 90.33% to 92.12%. There were excellent negative predictive values above 93% in all image sets. The software was able to monitor DR progression between baseline and follow-up images with the changes visualized. No cases of proliferative DR or DME were missed in the referable recommendations.

Conclusions

The DAPHNE automated software demonstrated its ability not only to grade images but also to reliably monitor and visualize progression. Therefore it has the potential to assist timely image analysis in patients with diabetes in varied populations and also help to discover subtle signs of sight-threatening disease onset.

Translational Relevance

This article takes research on machine vision and evaluates its readiness for clinical use.

Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning

Center-involved diabetic macular edema (ci-DME) is a major cause of vision loss. Although the gold standard for diagnosis involves 3D imaging, 2D imaging by fundus photography is usually used in screening settings, resulting in high false-positive and false-negative calls. To address this, we train a deep learning model to predict ci-DME from fundus photographs, with an ROC-AUC of 0.89 (95% CI: 0.87-0.91), corresponding to 85% sensitivity at 80% specificity. In comparison, retinal specialists have similar sensitivities (82-85%), but only half the specificity (45-50%, p < 0.001). Our model can also detect the presence of intraretinal fluid (AUC: 0.81; 95% CI: 0.81-0.86) and subretinal fluid (AUC 0.88; 95% CI: 0.85-0.91). Using deep learning to make predictions via simple 2D images without sophisticated 3D-imaging equipment and with better than specialist performance, has broad relevance to many other applications in medical imaging.

Diabetic retinopathy detection using red lesion localization and convolutional neural networks

Detecting the early signs of diabetic retinopathy (DR) is essential, as timely treatment might reduce or even prevent vision loss. Moreover, automatically localizing the regions of the retinal image that might contain lesions can favorably assist specialists in the task of detection. In this study, we designed a lesion localization model using a deep network patch-based approach. Our goal was to reduce the complexity of the model while improving its performance. For this purpose, we designed an efficient procedure (including two convolutional neural network models) for selecting the training patches, such that the challenging examples would be given special attention during the training process. Using the labeling of the region, a DR decision can be given to the initial image, without the need for special training. The model is trained on the Standard Diabetic Retinopathy Database, Calibration Level 1 (DIARETDB1) database and is tested on several databases (including Messidor) without any further adaptation. It reaches an area under the receiver operating characteristic curve of 0.912-95%CI(0.897-0.928) for DR screening, and a sensitivity of 0.940-95%CI(0.921-0.959). These values are competitive with other state-of-the-art approaches.

Changes in Retinal Microcirculation Precede the Clinical Onset of Diabetic Retinopathy in Children With Type 1 Diabetes Mellitus

PURPOSE

To investigate whether abnormal glucose metabolism in diabetes mellitus (DM) affects the retinal microcirculation of children with well-controlled type 1 DM and to compare these results with those obtained from healthy children.

DESIGN

Cross-sectional prospective study.

METHODS

This study enrolled 60 patients with DM without clinically detectable diabetic retinopathy (DR) and 57 age-matched control subjects. Optical coherence tomography angiography (OCT-A) was performed using AngioVue (Avanti, Optivue). Foveal avascular zone (FAZ) area, nonflow area, superficial and deep vessel densities, FAZ perimeter, acircularity index of FAZ (AI; the ratio of the perimeter of FAZ and the perimeter of a circle with equal area), and foveal density (FD-300; vessel density in 300 μm around FAZ) were analyzed. Correlations between the investigated OCT-A parameters with DM duration and glycated hemoglobin (HbA1c) levels were evaluated among patients with type 1 DM.

RESULTS

Differences in the mean values for FAZ perimeter, AI, and FD-300 were statistically significant between DM group and control group (P < .001, P = .001, and P = .009, respectively). There were also statistically significant differences between the groups for vessel densities of deep superior hemi-parafovea, deep temporal parafovea, and deep superior parafoveal zones (P = .008, P = .015, and P = .005, respectively). There were no significant correlations between DM duration and HbA1c levels with the investigated OCT-A parameters.

CONCLUSION

Diabetic eyes without clinically detectable DR exhibited alterations in FD-300, AI, perimeter, and vessel density of parafoveal capillaries in deep capillary plexus preceding the enlargement of FAZ; therefore, these new parameters might be sensitive imaging biomarkers to define early DR.

The Value of Automated Diabetic Retinopathy Screening with the EyeArt System: A Study of More Than 100,000 Consecutive Encounters from People with Diabetes

Background: Current manual diabetic retinopathy (DR) screening using eye care experts cannot scale to screen the growing population of diabetes patients who are at risk for vision loss. EyeArt system is an automated, cloud-based artificial intelligence (AI) eye screening technology designed to easily detect referral-warranted DR immediately through automated analysis of patient's retinal images. Methods: This retrospective study assessed the diagnostic efficacy of the EyeArt system v2.0 analyzing 850,908 fundus images from 101,710 consecutive patient visits, collected from 404 primary care clinics. Presence or absence of referral-warranted DR (more than mild nonproliferative DR [NPDR]) was automatically detected by the EyeArt system for each patient encounter, and its performance was compared against a clinical reference standard of quality-assured grading by rigorously trained certified ophthalmologists and optometrists. Results: Of the 101,710 visits, 75.7% were nonreferable, 19.3% were referable to an eye care specialist, and in 5.0%, the DR level was unknown as per the clinical reference standard. EyeArt screening had 91.3% (95% confidence interval [CI]: 90.9-91.7) sensitivity and 91.1% (95% CI: 90.9-91.3) specificity. For 5446 encounters with potentially treatable DR (more than moderate NPDR and/or diabetic macular edema), the system provided a positive "refer" output to 5363 encounters achieving sensitivity of 98.5%. Conclusions: This study captures variations in real-world clinical practice and shows that an AI DR screening system can be safe and effective in the real world. This study demonstrates the value of this easy-to-use, automated tool for endocrinologists, diabetologists, and general practitioners to address the growing need for DR screening and monitoring.

Prevalence, incidence and future projection of diabetic eye disease in Europe: a systematic review and meta-analysis

To examine the prevalence and incidence of diabetic eye disease (DED) among individuals with diabetes in Europe, a systematic review to identify all published European prevalence and incidence studies of DED in individuals with diabetes managed in primary health care was performed according to the MOOSE and PRISMA guidelines. The databases Medline, Embase and Web of Science were searched to 2 September 2017. Meta-analyses and meta-regressions were performed. The pooled prevalence estimates were applied to diabetes prevalence rates provided by the International Diabetes Foundation atlas and Eurostat population data, and extrapolated to the year 2050. Data of 35 prevalence and four incidence studies were meta-analyzed. Any diabetic retinopathy (DR) and diabetic macular edema (DME) were prevalent in 25.7% (95% CI 22.8-28.8%) and 3.7% (95% CI 2.2-6.2%), respectively. In meta-regression, the prevalence of DR in persons with type 1 diabetes was significantly higher compared to persons with type 2 diabetes (54.4% vs. 25.0%). The pooled mean annual incidence of any DR and DME in in persons with type 2 diabetes was 4.6% (95% CI 2.3-8.8%) and 0.4% (95% CI 0.5-1.4%), respectively. We estimated that persons with diabetes affected by any DED in Europe will increase from 6.4 million today to 8.6 million in 2050, of whom 30% require close monitoring and/or treatment. DED is estimated to be present in more than a quarter of persons with type 2 diabetes and half of persons with type 1 diabetes underlining the importance of regular monitoring. Future health services need to be planned accordingly.

Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India

Importance

More than 60 million people in India have diabetes and are at risk for diabetic retinopathy (DR), a vision-threatening disease. Automated interpretation of retinal fundus photographs can help support and scale a robust screening program to detect DR.

Objective

To prospectively validate the performance of an automated DR system across 2 sites in India.

Design, Setting, and Participants

This prospective observational study was conducted at 2 eye care centers in India (Aravind Eye Hospital and Sankara Nethralaya) and included 3049 patients with diabetes. Data collection and patient enrollment took place between April 2016 and July 2016 at Aravind and May 2016 and April 2017 at Sankara Nethralaya. The model was trained and fixed in March 2016.

Interventions

Automated DR grading system compared with manual grading by 1 trained grader and 1 retina specialist from each site. Adjudication by a panel of 3 retinal specialists served as the reference standard in the cases of disagreement.

Main Outcomes and Measures

Sensitivity and specificity for moderate or worse DR or referable diabetic macula edema.

Results

Of 3049 patients, 1091 (35.8%) were women and the mean (SD) age for patients at Aravind and Sankara Nethralaya was 56.6 (9.0) years and 56.0 (10.0) years, respectively. For moderate or worse DR, the sensitivity and specificity for manual grading by individual nonadjudicator graders ranged from 73.4% to 89.8% and from 83.5% to 98.7%, respectively. The automated DR system's performance was equal to or exceeded manual grading, with an 88.9% sensitivity (95% CI, 85.8-91.5), 92.2% specificity (95% CI, 90.3-93.8), and an area under the curve of 0.963 on the data set from Aravind Eye Hospital and 92.1% sensitivity (95% CI, 90.1-93.8), 95.2% specificity (95% CI, 94.2-96.1), and an area under the curve of 0.980 on the data set from Sankara Nethralaya.

Conclusions and Relevance

This study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.

Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program

Deep learning algorithms have been used to detect diabetic retinopathy (DR) with specialist-level accuracy. This study aims to validate one such algorithm on a large-scale clinical population, and compare the algorithm performance with that of human graders. A total of 25,326 gradable retinal images of patients with diabetes from the community-based, nationwide screening program of DR in Thailand were analyzed for DR severity and referable diabetic macular edema (DME). Grades adjudicated by a panel of international retinal specialists served as the reference standard. Relative to human graders, for detecting referable DR (moderate NPDR or worse), the deep learning algorithm had significantly higher sensitivity (0.97 vs. 0.74, p < 0.001), and a slightly lower specificity (0.96 vs. 0.98, p < 0.001). Higher sensitivity of the algorithm was also observed for each of the categories of severe or worse NPDR, PDR, and DME (p < 0.001 for all comparisons). The quadratic-weighted kappa for determination of DR severity levels by the algorithm and human graders was 0.85 and 0.78 respectively (p < 0.001 for the difference). Across different severity levels of DR for determining referable disease, deep learning significantly reduced the false negative rate (by 23%) at the cost of slightly higher false positive rates (2%). Deep learning algorithms may serve as a valuable tool for DR screening.

Choroidal Thickness and Ganglion Cell Complex in Pubescent Children with Type 1 Diabetes without Diabetic Retinopathy Analyzed by Spectral Domain Optical Coherence Tomography

AIM

To assess the retinal and choroidal thickness and ganglion cell complex (GCC) in pubescent children with type 1 diabetes (T1D) without diabetic retinopathy (DR), using spectral domain optical coherence tomography (SD-OCT).

MATERIALS AND METHOD

Sixty-four right eyes of 64 subjects with T1D and 45 right eyes of 45 age-matched healthy volunteers (control group) were enrolled in this study. The mean age of the subjects and controls was 15.3 (±SD = 2.2) and 14.6 (±SD = 1.5), respectively. SD-OCT was performed using RTVue XR Avanti. Ganglion cell complex (GCC), GCC focal loss volume (FLV), GCC global loss volume (GLV), choroidal thickness (CT), foveal (FT) and parafoveal thickness (PFT), and foveal (FV) and parafoveal volume (PFV) data were analyzed.

RESULTS

There was no significant difference between subjects and controls in the CT in the fovea and nasal, temporal, superior, and inferior quadrants of the macula. There were no significant correlations between CT, duration of diabetes, and HbA1C level (p = 0.272 and p = 0.197, resp.). GCC thickness did not differ significantly between the groups (p = 0.448), but there was a significant difference in FLV (p = 0.037). Significant differences between the groups were found in the PFT and PFV (p = 0.004 and p = 0.005, resp.). There was a significant negative correlation between PFT, PFV, and HbA1C level (p = 0.002 and p = 0.001, resp.).

CONCLUSIONS

Choroidal thickness remains unchanged in children with T1D. Increased GCC FLV might suggest an early alteration in neuroretinal tissue. Parafoveal retinal thickness is decreased in pubescent T1D children and correlates with HbA1C level. OCT can be considered a part of noninvasive screening in children with T1D and a tool for early detection of retinal and choroidal abnormalities. Further OCT follow-up is needed to determine whether any of the discussed OCT measurements are predictive of future DR severity.

Optical coherence tomography angiography vessel density in children with type 1 diabetes

PURPOSE

To assess the optical coherence tomography angiography (OCTA) retinal vessel density and foveal avascular zone (FAZ) in children with type 1 diabetes (T1D) and compare potential pathologic early changes in this population to healthy age-matched controls.

METHODS

This study included 130 pubescent children: 94 with T1D (188 eyes) and 36 of their age-matched control group (60 eyes). OCTA was performed using AngioVue (Avanti, Optivue). FAZ area (mm2) in superficial plexus, whole superficial capillary vessel density (wsVD), fovea superficial vessel density (fsVD), parafovea superficial vessel density (psVD), whole deep vessel density (wdVD), fovea deep vessel density (fdVD), parafovea deep vessel density (pdVD), foveal thickness (FT) (μm) and parafoveal thickness (PFT) (μm) were taken into analysis. Among the studied patients with T1D there were assessed codependences regarding the investigated foveal and parafoveal parameters and selected potential predictors, i.e. patient's age (years), diabetes duration time (years), age of onset of the disease (years), mean level of glycated hemoglobin (HbA1C) (%), and concentration of serum creatinine (mg/dL).

RESULTS

None of the abovementioned OCT and OCTA parameters was statistically significantly different between the groups. The patient's age statistically significantly did not influent any of the OCT and OCTA parameters. Yet an elevated level of HbA1C tended to reduce the parafovea superficial vessel density (p = 0.039), and parafoveal thickness (p = 0.003) and an increased serum creatinine level correlated with the decreased whole deep vessel density (p < 0.001). The parafovea deep vessel density in the diabetic patients decreased when the serum creatinine level (p = 0.008), age of onset of the disease (p = 0.028), and diabetes duration time (p = 0.014) rose.

CONCLUSIONS

Vessel density, both in superficial and deep plexuses, and FAZ area are normal in pubescent children with T1D comparing to healthy subjects. An elevated level of HbA1C correlated with reduced psVD and PFT. Longitudinal observation of these young patients is needed to determine if any of these OCTA measurements are predictive of future DR severity.

Acircularity index and axis ratio of the foveal avascular zone in diabetic eyes and healthy controls measured by optical coherence tomography angiography

Given the complexity of the current system used to stage diabetic retinopathy (DR) and the risks and limitations associated with intravenous fluorescein angiography (IVFA), noninvasive quantification of DR severity is desirable. We examined the utility of acircularity index and axis ratio of the foveal avascular zone (FAZ), metrics that can noninvasively quantify the severity of diabetic retinopathy without the need for axial length to correct for individual retinal magnification. A retrospective review was performed of type 2 diabetics and age-matched controls imaged with optical coherence tomography angiography (OCTA). Diabetic eyes were divided into three groups according to clinical features: No clinically observable diabetic retinopathy (NoDR), nonproliferative diabetic retinopathy (NPDR), and proliferative diabetic retinopathy (PDR). OCTAs of the superficial and deep vascular layers centered at the fovea were superimposed to form a full vascular layer on which the FAZ was manually traced. Acircularity index and axis ratio were calculated for each FAZ. Significant differences in acircularity index were observed between all groups except for controls vs. NoDR. Similar results were found for axis ratio, although there was no significant difference observed between NPDR and PDR. We demonstrate that acircularity index and axis ratio can be used to help noninvasively stage DR using OCTA, and show promise as methods to monitor disease progression and detect response to treatment.

Putative protective role of lutein and zeaxanthin in diabetic retinopathy

Diabetic retinopathy (DR) is one of the most important microvascular complications of diabetes and remains the leading cause of blindness in the working-age individuals. The exact aetiopathogenesis of DR remains elusive despite major advances in basic science and clinical research. Oxidative damage as one of the underlying causes for DR is increasingly being recognised. In humans, three hydroxycarotenoids, lutein (L), zeaxanthin (Z) and meso-zeaxanthin (MZ), accumulate at the central retina (to the exclusion of all other dietary carotenoids), where they are collectively known as macular pigment. These hydroxycarotenoids by nature of their biochemical structure and function help neutralise reactive oxygen species, and thereby, prevent oxidative damage to the retina (biological antioxidants). Apart from their key antioxidant function, evidence is emerging that these carotenoids may also exhibit neuroprotective and anti-inflammatory function in the retina. Since the preliminary identification of hydroxycarotenoid in the human macula by Wald in the 1940s, there has been astounding progress in our knowledge of the role of these carotenoids in promoting ocular health. While the Age-Related Eye Disease Study 2 has established a clinical benefit for L and Z supplements in patients with age-related macular degeneration, the role of these carotenoids in other retinal diseases potentially linked to oxidative damage remains unclear. In this article, we comprehensively review the literature germane to the putative protective role of two hydroxycarotenoids, L and Z, in the pathogenesis of DR.

Stakeholders’ perspectives on the management of diabetic retinopathy for a district health system – South Africa

Background: Clinical practice guidelines for the management of diabetic retinopathy (DR) adopted in various countries show variations in methods of examinations, screeners and classification systems. The South African National Guidelines for the frequency of referral of patients with diabetes mellitus (DM) for DR assessment were developed more than a decade ago. They do not specify the role of primary healthcare workers (PHCW) to manage DR at primary healthcare (PHC) level. The primary objective of this study was to establish the current role of PHCW in managing diabetic eye disease.Method: A cross-sectional study was conducted, and questionnaires were distributed to a total of 181 healthcare practitioners (HCPs) in public health institutions situated in the northern eThekwini district of KwaZulu-Natal. Clinics and community health centres (CHCs) were selected based on the assumption that PHC nurses, general practitioners or medical officers (MOs) and ophthalmic nurses practice at these institutions. The hospitals selected were the referral institutions for the selected clinics and CHCs. The questionnaires distributed included questions relating to the DR classification systems usage, HCP interaction and opinions on how HCPs could be valuable in managing DR.Results: Only two out of the five ophthalmic nurses were familiar with the grading classification systems for DR. Ophthalmic nurses had less interaction with general practitioners or MOs (40.0%) than the PHC nurses (60.0%). Only 2.4% of the PHC nurses interacted with ophthalmologists. Four of the five ophthalmic nurses indicated that PHC nurses would be valuable in the management of DR by taking visual acuity (VA) and conducting a pinhole test. More than 60% of the general practitioners or MOs (65.6%) suggested that ophthalmic nurses do a fundus examination. Ophthalmologists indicated that the PHC nurses were the least capable (17.7%) to screen for DR.Conclusion: Primary healthcare workers such as PHC nurses, ophthalmic nurses, general practitioners or MOs and optometrists have specific roles to play in DR management, which includes its prevention, detection, grading, referral and monitoring.

The management of diabetic retinopathy in the public sector of eThekwini district of KwaZulu-Natal

Background: Estimates from the year 1990–2010 showed an increase in blindness and vision impairment (moderate or severe) because of diabetic retinopathy (DR) in Sub-Saharan Africa’s sub-regions (central, eastern, southern and western Africa).1 The rate of DR in South Africa is expected to increase because of the lack of screening protocols and policies for the management of diabetic eye disease in the district health system of South Africa. Aim: The purpose of this study was to determine the current role of healthcare practitioners (HCPs) towards managing DR in the eThekwini district of KwaZulu-Natal.Method: A cross-sectional study was conducted, and questionnaires were distributed to a total of 104 HCPs in public health institutions situated in the northern eThekwini district of KwaZulu-Natal. Clinics and community health centres (CHCs) were selected based on the assumption that primary healthcare nurses, medical officers (MOs) and ophthalmic nurses and/or optometrists practice at these institutions. The hospitals selected were the referral institutions for the selected clinics and CHCs. The questionnaires distributed included questions relating to diabetic patient registers, referrals to and from other HCPs, management of ocular complications, ocular screening methods, fundus examinations and involvement in screening programmes.Results: Over a third of the ophthalmologists (35.3%) indicated that DR was present at the initial examination in more than 50% of patients, though overall ophthalmologists reported loss of vision in at least one eye in fewer than 5% of patients on presentation. Less than half of the public sector general practitioners or MOs (40.6%) conducted fundus examinations but 90.6% did not dilate pupils, although 71.9% had knowledge on the use of a direct ophthalmoscope. Only 40.6% of the MOs discussed the ocular complications of uncontrolled diabetes mellitus (DM) with patients and 62.5% encouraged regular eye examinations. Less than 50% of the MOs (43.8%) referred patients complaining of visual difficulties to optometrists and 9.4% referred to the ophthalmic nurses. Only 6.25% referred patients with DM needing further evaluation to ophthalmologists. Data from the optometrists were inconclusive because of the poor response rate of 5 (20%). None of the ophthalmic nurses reported doing fundus photography or refractions. Two-thirds of the ophthalmic nurses were interested in training to properly grade DR.Conclusion: The study established that there are key challenges in referral, training and practice in the management of DR. These need to be addressed in order to develop a comprehensive approach for the prevention and management of visual impairment and blindness because of DM.

Activation of endogenous angiotensin converting enzyme 2 prevents early injuries induced by hyperglycemia in rat retina

Diabetic retinopathy (DR) is a serious complication of diabetes mellitus that may result in blindness. We evaluated the effects of activation of endogenous angiotensin converting enzyme (ACE) 2 on the early stages of DR. Rats were administered an intravenous injection of streptozotocin to induce hyperglycemia. The ACE2 activator 1-[[2-(dimethylamino) ethyl] amino]-4-(hydroxymethyl)-7-[[(4-methylphenyl) sulfonyl] oxy]-9H-xanthone 9 (XNT) was administered by daily gavage. The death of retinal ganglion cells (RGC) was evaluated in histological sections, and retinal ACE2, caspase-3, and vascular endothelial growth factor (VEGF) expressions were analyzed by immunohistochemistry. XNT treatment increased ACE2 expression in retinas of hyperglycemic (HG) rats (control: 13.81±2.71 area%; HG: 14.29±4.30 area%; HG+XNT: 26.87±1.86 area%; P<0.05). Importantly, ACE2 activation significantly increased the RCG number in comparison with HG animals (control: 553.5±14.29; HG: 530.8±10.3 cells; HG+XNT: 575.3±16.5 cells; P<0.05). This effect was accompanied by a reduction in the expression of caspase-3 in RGC of the HG+XNT group when compared with untreated HG rats (control: 18.74±1.59; HG: 38.39±3.39 area%; HG+XNT: 27.83±2.80 area%; P<0.05). Treatment with XNT did not alter the VEGF expression in HG animals (P>0.05). Altogether, these findings indicate that activation of ACE2 reduced the death of retinal ganglion cells by apoptosis in HG rats.

Current trends in the monitoring and treatment of diabetic retinopathy in young adults

The diagnosis and treatment of diabetic retinopathy (DR) in young adults have significantly improved in recent years. Research methods have widened significantly, for example, by introducing spectral optical tomography of the eye. Invasive diagnostics, for example, fluorescein angiography, are done less frequently. The early introduction of an insulin pump to improve the administration of insulin is likely to delay the development of diabetic retinopathy, which is particularly important for young patients with type 1 diabetes mellitus (T1DM). The first years of diabetes occurring during childhood and youth are the most appropriate to introduce proper therapeutic intervention before any irreversible changes in the eyes appear. The treatment of DR includes increased metabolic control, laserotherapy, pharmacological treatment (antiangiogenic and anti-inflammatory treatment, enzymatic vitreolysis, and intravitreal injections), and surgery. This paper summarizes the up-to-date developments in the diagnostics and treatment of DR. In the literature search, authors used online databases, PubMed, and clinitrials.gov and browsed through individual ophthalmology journals, books, and leading pharmaceutical company websites.