Automated machine learning model for fundus image classification by health-care professionals with no coding experience.

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

Optical coherence tomography angiography for detection of microvascular changes in early diabetes: A systematic review and meta-analysis.

AIMS: To evaluate the effectiveness of optical coherence tomography angiography (OCTA) in detecting early intraocular microvascular changes in diabetic patients. MATERIALS AND METHODS: A systematic study search was performed on PubMed, Medline, Embase, and the Cochrane Library, ranging from January 2012 to March 2023. Controlled studies compared diabetes mellitus (DM) patients with non-diabetic retinopathy (NDR) or patients with mild non-proliferative diabetic retinopathy (mild NPDR) to healthy people. These studies included parameters of OCTA such as foveal avascular zone (FAZ), vessel density of superficial capillary plexus (VDscp), vessel density of deep capillary plexus (VDdcp), and peripapillary VD. The relevant effect model was used according to the heterogeneity, and the mean difference and 95% confidence intervals were calculated. RESULTS: A total of 18 studies with 2101 eyes were eventually included in this meta-analysis. Our results demonstrated that early alterations of VDscp, VDdcp, and peripapillary VD in NDR patients had a significant difference compared with healthy people by OCTA (VDscp: WMD = -1.34, 95% CI: -1.99 to -0.68, P < 0.0001. VDdcp: WMD = -2.00, 95% CI: -2.95 to -1.04, P < 0.0001. Peripapillary VD: WMD = -1.07, 95% CI: -1.70 to -0.43, P = 0.0010). However, there was no statistically significant difference in total FAZ between them (WMD = -0.00, 95% CI: -0.02-0.01, P = 0.84). In addition, for patients with mild NPDR, OCTA could illustrate prominent changes in VDscp, VDdcp, and total FAZ compared with healthy people (VDscp: WMD = -6.11, 95% CI: -9.90 to -2.32, P = 0.002. VDdcp: WMD = -4.26, 95% CI: -5.95 to -2.57, P < 0.00001. FAZ: WMD = 0.06, 95% CI: 0.01-0.11, P = 0.03). CONCLUSIONS: In diabetic patients with or without retinopathy, the parameters of OCTA such as VDscp, VDdcp, and peripapillary vessel density were demonstrated as potential biomarkers in monitoring the early alterations of retinal microangiopathy, while total FAZ may have no significant changes in diabetic patients without retinopathy.

Comparison of 21 artificial intelligence algorithms in automated diabetic retinopathy screening using handheld fundus camera.

BACKGROUND: Diabetic retinopathy (DR) is a common complication of diabetes and may lead to irreversible visual loss. Efficient screening and improved treatment of both diabetes and DR have amended visual prognosis for DR. The number of patients with diabetes is increasing and telemedicine, mobile handheld devices and automated solutions may alleviate the burden for healthcare. We compared the performance of 21 artificial intelligence (AI) algorithms for referable DR screening in datasets taken by handheld Optomed Aurora fundus camera in a real-world setting. PATIENTS AND METHODS: Prospective study of 156 patients (312 eyes) attending DR screening and follow-up. Both papilla- and macula-centred 50° fundus images were taken from each eye. DR was graded by experienced ophthalmologists and 21 AI algorithms. RESULTS: Most eyes, 183 out of 312 (58.7%), had no DR and mild NPDR was noted in 21 (6.7%) of the eyes. Moderate NPDR was detected in 66 (21.2%) of the eyes, severe NPDR in 1 (0.3%), and PDR in 41 (13.1%) composing a group of 34.6% of eyes with referable DR. The AI algorithms achieved a mean agreement of 79.4% for referable DR, but the results varied from 49.4% to 92.3%. The mean sensitivity for referable DR was 77.5% (95% CI 69.1-85.8) and specificity 80.6% (95% CI 72.1-89.2). The rate for images ungradable by AI varied from 0% to 28.2% (mean 1.9%). Nineteen out of 21 (90.5%) AI algorithms resulted in grading for DR at least in 98% of the images. CONCLUSIONS: Fundus images captured with Optomed Aurora were suitable for DR screening. The performance of the AI algorithms varied considerably emphasizing the need for external validation of screening algorithms in real-world settings before their clinical application.

What is already known on this topic? Diabetic retinopathy (DR) is a common complication of diabetes. Efficient screening and timely treatment are important to avoid the development of sight-threatening DR. The increasing number of patients with diabetes and DR poses a challenge for healthcare.What this study adds? Telemedicine, mobile handheld devices and artificial intelligence (AI)-based automated algorithms are likely to alleviate the burden by improving efficacy of DR screening programs. Reliable algorithms of high quality exist despite the variability between the solutions.How this study might affect research, practice or policy? AI algorithms improve the efficacy of screening and might be implemented to clinical use after thorough validation in a real-life setting.

CauDR: A causality-inspired domain generalization framework for fundus-based diabetic retinopathy grading.

Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR. Diabetic retinopathy (DR) is the most common diabetic complication, which usually leads to retinal damage, vision loss, and even blindness. A computer-aided DR grading system has a significant impact on helping ophthalmologists with rapid screening and diagnosis. Recent advances in fundus photography have precipitated the development of novel retinal imaging cameras and their subsequent implementation in clinical practice. However, most deep learning-based algorithms for DR grading demonstrate limited generalization across domains. This inferior performance stems from variance in imaging protocols and devices inducing domain shifts. We posit that declining model performance between domains arises from learning spurious correlations in the data. Incorporating do-operations from causality analysis into model architectures may mitigate this issue and improve generalizability. Specifically, a novel universal structural causal model (SCM) was proposed to analyze spurious correlations in fundus imaging. Building on this, a causality-inspired diabetic retinopathy grading framework named CauDR was developed to eliminate spurious correlations and achieve more generalizable DR diagnostics. Furthermore, existing datasets were reorganized into 4DR benchmark for DG scenario. Results demonstrate the effectiveness and the state-of-the-art (SOTA) performance of CauDR.

Diabetic retinopathy prediction based on vision transformer and modified capsule network.

Diabetic retinopathy is considered one of the most common diseases that can lead to blindness in the working age, and the chance of developing it increases as long as a person suffers from diabetes. Protecting the sight of the patient or decelerating the evolution of this disease depends on its early detection as well as identifying the exact levels of this pathology, which is done manually by ophthalmologists. This manual process is very consuming in terms of the time and experience of an expert ophthalmologist, which makes developing an automated method to aid in the diagnosis of diabetic retinopathy an essential and urgent need. In this paper, we aim to propose a new hybrid deep learning method based on a fine-tuning vision transformer and a modified capsule network for automatic diabetic retinopathy severity level prediction. The proposed approach consists of a new range of computer vision operations, including the power law transformation technique and the contrast-limiting adaptive histogram equalization technique in the preprocessing step. While the classification step builds up on a fine-tuning vision transformer, a modified capsule network, and a classification model combined with a classification model, The effectiveness of our approach was evaluated using four datasets, including the APTOS, Messidor-2, DDR, and EyePACS datasets, for the task of severity levels of diabetic retinopathy. We have attained excellent test accuracy scores on the four datasets, respectively: 88.18%, 87.78%, 80.36%, and 78.64%. Comparing our results with the state-of-the-art, we reached a better performance.

Artificial intelligence-based prediction of diabetic retinopathy evolution (EviRed): protocol for a prospective cohort.

INTRODUCTION: An important obstacle in the fight against diabetic retinopathy (DR) is the use of a classification system based on old imaging techniques and insufficient data to accurately predict its evolution. New imaging techniques generate new valuable data, but we lack an adapted classification based on these data. The main objective of the Evaluation Intelligente de la Rétinopathie Diabétique, Intelligent evaluation of DR (EviRed) project is to develop and validate a system assisting the ophthalmologist in decision-making during DR follow-up by improving the prediction of its evolution. METHODS AND ANALYSIS: A cohort of up to 5000 patients with diabetes will be recruited from 18 diabetology departments and 14 ophthalmology departments, in public or private hospitals in France and followed for an average of 2 years. Each year, systemic health data as well as ophthalmological data will be collected. Both eyes will be imaged by using different imaging modalities including widefield photography, optical coherence tomography (OCT) and OCT-angiography. The EviRed cohort will be divided into two groups: one group will be randomly selected in each stratum during the inclusion period to be representative of the general diabetic population. Their data will be used for validating the algorithms (validation cohort). The data for the remaining patients (training cohort) will be used to train the algorithms. ETHICS AND DISSEMINATION: The study protocol was approved by the French South-West and Overseas Ethics Committee 4 on 28 August 2020 (CPP2020-07-060b/2020-A01725-34/20.06.16.41433). Prior to the start of the study, each patient will provide a written informed consent documenting his or her agreement to participate in the clinical trial. Results of this research will be disseminated in peer-reviewed publications and conference presentations. The database will also be available for further study or development that could benefit patients. TRIAL REGISTRATION NUMBER: NCT04624737.

OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods.

Optical coherence tomography (OCT) is a non-invasive imaging technique with extensive clinical applications in ophthalmology. OCT enables the visualization of the retinal layers, playing a vital role in the early detection and monitoring of retinal diseases. OCT uses the principle of light wave interference to create detailed images of the retinal microstructures, making it a valuable tool for diagnosing ocular conditions. This work presents an open-access OCT dataset (OCTDL) comprising over 2000 OCT images labeled according to disease group and retinal pathology. The dataset consists of OCT records of patients with Age-related Macular Degeneration (AMD), Diabetic Macular Edema (DME), Epiretinal Membrane (ERM), Retinal Artery Occlusion (RAO), Retinal Vein Occlusion (RVO), and Vitreomacular Interface Disease (VID). The images were acquired with an Optovue Avanti RTVue XR using raster scanning protocols with dynamic scan length and image resolution. Each retinal b-scan was acquired by centering on the fovea and interpreted and cataloged by an experienced retinal specialist. In this work, we applied Deep Learning classification techniques to this new open-access dataset.

A new intelligent system based deep learning to detect DME and AMD in OCT images.

Optical Coherence Tomography (OCT) is widely recognized as the leading modality for assessing ocular retinal diseases, playing a crucial role in diagnosing retinopathy while maintaining a non-invasive modality. The increasing volume of OCT images underscores the growing importance of automating image analysis. Age-related diabetic Macular Degeneration (AMD) and Diabetic Macular Edema (DME) are the most common cause of visual impairment. Early detection and timely intervention for diabetes-related conditions are essential for preventing optical complications and reducing the risk of blindness. This study introduces a novel Computer-Aided Diagnosis (CAD) system based on a Convolutional Neural Network (CNN) model, aiming to identify and classify OCT retinal images into AMD, DME, and Normal classes. Leveraging CNN efficiency, including feature learning and classification, various CNN, including pre-trained VGG16, VGG19, Inception_V3, a custom from scratch model, BCNN (VGG16) 2 , BCNN (VGG19) 2 , and BCNN (Inception_V3) 2 , are developed for the classification of AMD, DME, and Normal OCT images. The proposed approach has been evaluated on two datasets, including a DUKE public dataset and a Tunisian private dataset. The combination of the Inception_V3 model and the extracted feature from the proposed custom CNN achieved the highest accuracy value of 99.53% in the DUKE dataset. The obtained results on DUKE public and Tunisian datasets demonstrate the proposed approach as a significant tool for efficient and automatic retinal OCT image classification.

Source-free active domain adaptation for diabetic retinopathy grading based on ultra-wide-field fundus images.

Domain adaptation (DA) is commonly employed in diabetic retinopathy (DR) grading using unannotated fundus images, allowing knowledge transfer from labeled color fundus images. Existing DAs often struggle with domain disparities, hindering DR grading performance compared to clinical diagnosis. A source-free active domain adaptation method (SFADA), which generates features of color fundus images by noise, selects valuable ultra-wide-field (UWF) fundus images through local representation matching, and adapts models using DR lesion prototypes, is proposed to upgrade DR diagnostic accuracy. Importantly, SFADA enhances data security and patient privacy by excluding source domain data. It reduces image resolution and boosts model training speed by modeling DR grade relationships directly. Experiments show SFADA significantly improves DR grading performance, increasing accuracy by 20.90% and quadratic weighted kappa by 18.63% over baseline, reaching 85.36% and 92.38%, respectively. This suggests SFADA's promise for real clinical applications.

Computer aided diagnosis of diabetic retinopathy based on multi-view joint learning.

Diabetic retinopathy (DR) is a kind of ocular complication of diabetes, and its degree grade is an essential basis for early diagnosis of patients. Manual diagnosis is a long and expensive process with a specific risk of misdiagnosis. Computer-aided diagnosis can provide more accurate and practical treatment recommendations. In this paper, we propose a multi-view joint learning DR diagnostic model called RT2Net, which integrates the global features of fundus images and the local detailed features of vascular images to reduce the limitations of single fundus image learning. Firstly, the original image is preprocessed using operations such as contrast-limited adaptive histogram equalization, and the vascular structure of the extracted DR image is segmented. Then, the vascular image and fundus image are input into two branch networks of RT2Net for feature extraction, respectively, and the feature fusion module adaptively fuses the feature vectors' output from the branch networks. Finally, the optimized classification model is used to identify the five categories of DR. This paper conducts extensive experiments on the public datasets EyePACS and APTOS 2019 to demonstrate the method's effectiveness. The accuracy of RT2Net on the two datasets reaches 88.2% and 85.4%, and the area under the receiver operating characteristic curve (AUC) is 0.98 and 0.96, respectively. The excellent classification ability of RT2Net for DR can significantly help patients detect and treat lesions early and provide doctors with a more reliable diagnosis basis, which has significant clinical value for diagnosing DR.

Machine learning and optical coherence tomography-derived radiomics analysis to predict persistent diabetic macular edema in patients undergoing anti-VEGF intravitreal therapy.

BACKGROUND: Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. This study aimed to develop and evaluate an OCT-omics prediction model for assessing anti-vascular endothelial growth factor (VEGF) treatment response in patients with DME. METHODS: A retrospective analysis of 113 eyes from 82 patients with DME was conducted. Comprehensive feature engineering was applied to clinical and optical coherence tomography (OCT) data. Logistic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained using a training set of 79 eyes, and evaluated on a test set of 34 eyes. Clinical implications of the OCT-omics prediction model were assessed by decision curve analysis. Performance metrics (sensitivity, specificity, F1 score, and AUC) were calculated. RESULTS: The logistic, SVM, and BPNN classifiers demonstrated robust discriminative abilities in both the training and test sets. In the training set, the logistic classifier achieved a sensitivity of 0.904, specificity of 0.741, F1 score of 0.887, and AUC of 0.910. The SVM classifier showed a sensitivity of 0.923, specificity of 0.667, F1 score of 0.881, and AUC of 0.897. The BPNN classifier exhibited a sensitivity of 0.962, specificity of 0.926, F1 score of 0.962, and AUC of 0.982. Similar discriminative capabilities were maintained in the test set. The OCT-omics scores were significantly higher in the non-persistent DME group than in the persistent DME group (p < 0.001). OCT-omics scores were also positively correlated with the rate of decline in central subfield thickness after treatment (Pearson's R = 0.44, p < 0.001). CONCLUSION: The developed OCT-omics model accurately assesses anti-VEGF treatment response in DME patients. The model's robust performance and clinical implications highlight its utility as a non-invasive tool for personalized treatment prediction and retinal pathology assessment.

Sustained release gel based on CT image inspection for treatment of diabetes fundus macular lesions.

Currently, slow-release gel therapy is considered to be an effective treatment for fundus macular disease, but the lack of effective evaluation methods limits its clinical application. Therefore, the purpose of this study was to investigate the application and clinical effect of slow-release gel based on CT image examination in the treatment of diabetic fundus macular disease. CT images of fundus macular lesions were collected in a group of diabetic patients. Then the professional image processing software is used to process and analyze the image and extract the key parameters. A slow-release gel was designed and prepared, and applied to the treatment of diabetic fundus macular disease. CT images before and after treatment were compared and analyzed, and the effect of slow-release gel was evaluated. In a certain period of time after treatment, the lesion size and lesion degree of diabetic fundus macular disease were significantly improved by using slow-release gel therapy with CT image examination. No significant adverse reactions or complications were observed during the treatment. This indicates that the slow-release gel based on CT image examination is a safe, effective and feasible treatment method for diabetic fundus macular disease. This method can help improve the vision and quality of life of patients, and provide a new idea and plan for clinical treatment.

Reduced macular thickness and vascular density in abnormal glucose metabolism patients: A meta-analysis of optical coherence tomography (OCT) and OCT angiography studies.

BACKGROUND: Alterations in macular thickness and vascular density before clinically visible diabetic retinopathy (DR) remain inconclusive. This study aimed to determine whether retinal manifestations in abnormal glucose metabolism (AGM) patients differ from those in the healthy individuals. METHODS: PubMed, Embase, and Web of Science were searched between 2000 and 2021. The eligibility criteria were AGM patients without DR. Primary and secondary outcomes measured by optical coherence tomography (OCT) and OCT angiography (OCTA) were analyzed and expressed as standardized mean differences (SMDs) with 95% confidence intervals (CIs). A random-effects model was used in the data synthesis. The potential publication bias for the variables was evaluated using Egger's test. RESULTS: A total of 86 observational studies involving 13,773 participants and 15,416 eyes were included. OCT revealed that compared to healthy controls, the total macular thickness of AGM patients was thinner, including the thickness of fovea (-0.24, 95% CI [-0.39, -0.08]; P  = 0.002, I2  = 87.7%), all regions of parafovea (-0.32, 95% CI [-0.54, -0.11]; P  = 0.003; I2  = 71.7%) and the four quadrants of perifovea; the thickness of peripapillary retinal nerve fiber layer (pRNFL), macular retinal nerve fiber layer (mRNFL), and ganglion cell layer (GCL) also decreased. OCTA indicated that the superficial and deep vascular density decreased, the foveal avascular zone (FAZ) area enlarged, and the acircularity index (AI) reduced in AGM individuals. CONCLUSIONS: Retinal thinning and microvascular lesions have occurred before the advent of clinically detectable DR; OCT and OCTA may have the potential to detect these preclinical changes. REGISTRATION: PROSPERO; http://www.crd.york.ac.uk/prospero/ ; No. CRD42021269885.

A novel approach for intelligent diagnosis and grading of diabetic retinopathy.

Diabetic retinopathy (DR) is a severe ocular complication of diabetes that can lead to vision damage and even blindness. Currently, traditional deep convolutional neural networks (CNNs) used for DR grading tasks face two primary challenges: (1) insensitivity to minority classes due to imbalanced data distribution, and (2) neglecting the relationship between the left and right eyes by utilizing the fundus image of only one eye for training without differentiating between them. To tackle these challenges, we proposed the DRGCNN (DR Grading CNN) model. To solve the problem caused by imbalanced data distribution, our model adopts a more balanced strategy by allocating an equal number of channels to feature maps representing various DR categories. Furthermore, we introduce a CAM-EfficientNetV2-M encoder dedicated to encoding input retinal fundus images for feature vector generation. The number of parameters of our encoder is 52.88 M, which is less than RegNet_y_16gf (80.57 M) and EfficientNetB7 (63.79 M), but the corresponding kappa value is higher. Additionally, in order to take advantage of the binocular relationship, we input fundus retinal images from both eyes of the patient into the network for features fusion during the training phase. We achieved a kappa value of 86.62% on the EyePACS dataset and 86.16% on the Messidor-2 dataset. Experimental results on these representative datasets for diabetic retinopathy (DR) demonstrate the exceptional performance of our DRGCNN model, establishing it as a highly competitive intelligent classification model in the field of DR. The code is available for use at https://github.com/Fat-Hai/DRGCNN.

Explainable ensemble learning method for OCT detection with transfer learning.

The accuracy and interpretability of artificial intelligence (AI) are crucial for the advancement of optical coherence tomography (OCT) image detection, as it can greatly reduce the manual labor required by clinicians. By prioritizing these aspects during development and application, we can make significant progress towards streamlining the clinical workflow. In this paper, we propose an explainable ensemble approach that utilizes transfer learning to detect fundus lesion diseases through OCT imaging. Our study utilized a publicly available OCT dataset consisting of normal subjects, patients with dry age-related macular degeneration (AMD), and patients with diabetic macular edema (DME), each with 15 samples. The impact of pre-trained weights on the performance of individual networks was first compared, and then these networks were ensemble using majority soft polling. Finally, the features learned by the networks were visualized using Grad-CAM and CAM. The use of pre-trained ImageNet weights improved the performance from 68.17% to 92.89%. The ensemble model consisting of the three CNN models with pre-trained parameters loaded performed best, correctly distinguishing between AMD patients, DME patients and normal subjects 100% of the time. Visualization results showed that Grad-CAM could display the lesion area more accurately. It is demonstrated that the proposed approach could have good performance of both accuracy and interpretability in retinal OCT image detection.

The clinical evaluation of a widefield lens to expand the field of view in optical coherence tomography (OCT-A).

This study aimed to evaluate the clinical benefits of incorporating a widefield lens (WFL) in optical coherence tomography angiography (OCT-A) in patients with retinal vascular diseases in comparison to standard single-shot OCT-A scans. Sixty patients with retinal vascular diseases including diabetic retinopathy (DR) and retinal vein occlusion (RVO) were recruited. OCT-A imaging (PlexElite 9000) with and without WFL was performed in randomized order. The assessment included patient comfort, time, field of view (FoV), image quality and pathology detection. Statistical analysis included paired t-tests, Mann-Whitney U-tests and Bonferroni correction for multiple tests, with inter-grader agreement using the kappa coefficient. Using a WFL did not lead to statistically significant differences in DR and RVO group test times. Patient comfort remained high, with similar responses for WFL and non-WFL measurements. The WFL notably expanded the scan field (1.6× FoV increase), enhancing peripheral retinal visibility. However, image quality varied due to pathology and eye dominance, affecting the detection of peripheral issues in RVO and DR cases. The use of a WFL widens the scan field, aiding vascular retinal disease imaging with minor effects on comfort, time, and image quality. Further enhancements are needed for broader view angles, enabling improved quantification of non-perfused areas and more reliable peripheral proliferation detection.

Assessing Diabetic Retinopathy Staging With AI: A Comparative Analysis Between Pseudocolor and LED Imaging.

Purpose: To compare the diagnostic performance of artificial intelligence (AI)-based diabetic retinopathy (DR) staging system across pseudocolor, simulated white light (SWL), and light-emitting diode (LED) camera imaging modalities. Methods: A cross-sectional investigation involved patients with diabetes undergoing imaging with an iCare DRSplus confocal LED camera and an Optos confocal, ultra-widefield pseudocolor camera, with and without SWL. Macula-centered and optic nerve-centered 45 × 45-degree photographs were processed using EyeArt v2.1. Human graders established the ground truth (GT) for DR severity on dilated fundus exams. Sensitivity and weighted Cohen's weighted kappa (wκ) were calculated. An ordinal generalized linear mixed model identified factors influencing accurate DR staging. Results: The study included 362 eyes from 189 patients. The LED camera excelled in identifying sight-threatening DR stages (sensitivity = 0.83, specificity = 0.95 for proliferative DR) and had the highest agreement with the GT (wκ = 0.71). The addition of SWL to pseudocolor imaging resulted in decreased performance (sensitivity = 0.33, specificity = 0.98 for proliferative DR; wκ = 0.55). Peripheral lesions reduced the likelihood of being staged in the same or higher DR category by 80% (P < 0.001). Conclusions: Pseudocolor and LED cameras, although proficient, demonstrated non-interchangeable performance, with the LED camera exhibiting superior accuracy in identifying advanced DR stages. These findings underscore the importance of implementing AI systems trained for ultra-widefield imaging, considering the impact of peripheral lesions on correct DR staging. Translational Relevance: This study underscores the need for artificial intelligence-based systems specifically trained for ultra-widefield imaging in diabetic retinopathy assessment.

Association between albuminuria and retinal microvascular parameters measured with swept-source optical coherence tomography angiography in patients with diabetic retinopathy.

PURPOSE: To evaluate the relationship between urine albumin excretion (UAE) and retinal microvascular parameters assessed using swept-source optical coherence tomography angiography (SS-OCTA) in patients with diabetic retinopathy (DR). METHODS: This retrospective cross-sectional study included 180 patients with diabetes and 50 age-matched controls. Patients with diabetes were grouped according to the five-stage DR severity, combined with the presence of albuminuria. All subjects underwent 12×12mm2 field SS-OCTA. The foveal avascular zone metrics, vessel density, and capillary nonperfusion area (NPA) were quantified using a semi-automatic software algorithm on three different rectangular fields (3×3 mm2, 6×6 mm2, and 10×10 mm2). The correlations between albuminuria and the four OCTA parameters were analyzed. RESULTS: A total of 105 subjects had normal UAE, and 75 subjects had albuminuria. Of the 102 subjects whose DR severity was higher than mild non-proliferative DR (NPDR), capillary NPA on the 3×3 mm2, 6×6 mm2, and 10×10 mm2 fields was significantly larger in the albuminuria group. None of the OCTA parameters were significantly different between the two groups in subjects with mild NPDR or without DR. Multiple logistic regression analysis showed that an increase in NPA in the 6×6 mm2 and 10×10 mm2 fields was a significant risk factor for the presence of albuminuria (odds ratio = 1.92 and 1.35). CONCLUSION: An increase in capillary NPA was independently associated with albuminuria in patients with clinically significant DR levels. SS-OCTA imaging can be a useful marker for the early detection of diabetic nephropathy.

Vision transformer with masked autoencoders for referable diabetic retinopathy classification based on large-size retina image.

Computer-aided diagnosis systems based on deep learning algorithms have shown potential applications in rapid diagnosis of diabetic retinopathy (DR). Due to the superior performance of Transformer over convolutional neural networks (CNN) on natural images, we attempted to develop a new model to classify referable DR based on a limited number of large-size retinal images by using Transformer. Vision Transformer (ViT) with Masked Autoencoders (MAE) was applied in this study to improve the classification performance of referable DR. We collected over 100,000 publicly fundus retinal images larger than 224×224, and then pre-trained ViT on these retinal images using MAE. The pre-trained ViT was applied to classify referable DR, the performance was also compared with that of ViT pre-trained using ImageNet. The improvement in model classification performance by pre-training with over 100,000 retinal images using MAE is superior to that pre-trained with ImageNet. The accuracy, area under curve (AUC), highest sensitivity and highest specificity of the present model are 93.42%, 0.9853, 0.973 and 0.9539, respectively. This study shows that MAE can provide more flexibility to the input image and substantially reduce the number of images required. Meanwhile, the pretraining dataset scale in this study is much smaller than ImageNet, and the pre-trained weights from ImageNet are not required also.