Automated Diagnosis of Diabetic Retinopathy Using Clinical Biomarkers, Optical Coherence Tomography, and Optical Coherence Tomography Angiography

Identification of diabetic retinopathy classification using machine learning algorithms on clinical data and optical coherence tomography angiography

BACKGROUND

To apply machine learning (ML) algorithms to perform multiclass diabetic retinopathy (DR) classification using both clinical data and optical coherence tomography angiography (OCTA).

METHODS

In this cross-sectional observational study, clinical data and OCTA parameters from 203 diabetic patients (203 eye) were used to establish the ML models, and those from 169 diabetic patients (169 eye) were used for independent external validation. The random forest, gradient boosting machine (GBM), deep learning and logistic regression algorithms were used to identify the presence of DR, referable DR (RDR) and vision-threatening DR (VTDR). Four different variable patterns based on clinical data and OCTA variables were examined. The algorithms' performance were evaluated using receiver operating characteristic curves and the area under the curve (AUC) was used to assess predictive accuracy.

RESULTS

The random forest algorithm on OCTA+clinical data-based variables and OCTA+non-laboratory factor-based variables provided the higher AUC values for DR, RDR and VTDR. The GBM algorithm produced similar results, albeit with slightly lower AUC values. Leading predictors of DR status included vessel density, retinal thickness and GCC thickness, as well as the body mass index, waist-to-hip ratio and glucose-lowering treatment.

CONCLUSIONS

ML-based multiclass DR classification using OCTA and clinical data can provide reliable assistance for screening, referral, and management DR populations.

Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review

PURPOSE

This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools.

METHODS

This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included.

RESULTS

A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data.

CONCLUSION

AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

An AI-based novel system for predicting respiratory support in COVID-19 patients through CT imaging analysis

The proposed AI-based diagnostic system aims to predict the respiratory support required for COVID-19 patients by analyzing the correlation between COVID-19 lesions and the level of respiratory support provided to the patients. Computed tomography (CT) imaging will be used to analyze the three levels of respiratory support received by the patient: Level 0 (minimum support), Level 1 (non-invasive support such as soft oxygen), and Level 2 (invasive support such as mechanical ventilation). The system will begin by segmenting the COVID-19 lesions from the CT images and creating an appearance model for each lesion using a 2D, rotation-invariant, Markov-Gibbs random field (MGRF) model. Three MGRF-based models will be created, one for each level of respiratory support. This suggests that the system will be able to differentiate between different levels of severity in COVID-19 patients. The system will decide for each patient using a neural network-based fusion system, which combines the estimates of the Gibbs energy from the three MGRF-based models. The proposed system were assessed using 307 COVID-19-infected patients, achieving an accuracy of [Formula: see text], a sensitivity of [Formula: see text], and a specificity of [Formula: see text], indicating a high level of prediction accuracy.

Detection of systemic cardiovascular illnesses and cardiometabolic risk factors with machine learning and optical coherence tomography angiography: a pilot study

BACKGROUND/OBJECTIVES

Optical coherence tomography angiography (OCTA) has been found to identify changes in the retinal microvasculature of people with various cardiometabolic factors. Machine learning has previously been applied within ophthalmic imaging but has not yet been applied to these risk factors. The study aims to assess the feasibility of predicting the presence or absence of cardiovascular conditions and their associated risk factors using machine learning and OCTA.

METHODS

Cross-sectional study. Demographic and co-morbidity data was collected for each participant undergoing 3 × 3 mm, 6 × 6 mm and 8 × 8 mm OCTA scanning using the Carl Zeiss CIRRUS HD-OCT model 5000. The data was then pre-processed and randomly split into training and testing datasets (75%/25% split) before being applied to two models (Convolutional Neural Network and MoblieNetV2). Once developed on the training dataset, their performance was assessed on the unseen test dataset.

RESULTS

Two hundred forty-seven participants were included. Both models performed best in predicting the presence of hyperlipidaemia in 3 × 3 mm scans with an AUC of 0.74 and 0.81, and accuracy of 0.79 for CNN and MobileNetV2 respectively. Modest performance was achieved in the identification of diabetes mellitus, hypertension and congestive heart failure in 3 × 3 mm scans (all with AUC and accuracy >0.5). There was no significant recognition for 6 × 6 and 8 × 8 mm for any cardiometabolic risk factor.

CONCLUSION

This study demonstrates the strength of ML to identify the presence cardiometabolic factors, in particular hyperlipidaemia, in high-resolution 3 × 3 mm OCTA scans. Early detection of risk factors prior to a clinically significant event, will assist in preventing adverse outcomes for people.

Wavelet scattering transform application in classification of retinal abnormalities using OCT images

To assist ophthalmologists in diagnosing retinal abnormalities, Computer Aided Diagnosis has played a significant role. In this paper, a particular Convolutional Neural Network based on Wavelet Scattering Transform (WST) is used to detect one to four retinal abnormalities from Optical Coherence Tomography (OCT) images. Predefined wavelet filters in this network decrease the computation complexity and processing time compared to deep learning methods. We use two layers of the WST network to obtain a direct and efficient model. WST generates a sparse representation of the images which is translation-invariant and stable concerning local deformations. Next, a Principal Component Analysis classifies the extracted features. We evaluate the model using four publicly available datasets to have a comprehensive comparison with the literature. The accuracies of classifying the OCT images of the OCTID dataset into two and five classes were [Formula: see text] and [Formula: see text], respectively. We achieved an accuracy of [Formula: see text] in detecting Diabetic Macular Edema from Normal ones using the TOPCON device-based dataset. Heidelberg and Duke datasets contain DME, Age-related Macular Degeneration, and Normal classes, in which we achieved accuracy of [Formula: see text] and [Formula: see text], respectively. A comparison of our results with the state-of-the-art models shows that our model outperforms these models for some assessments or achieves nearly the best results reported so far while having a much smaller computational complexity.

Impact of Imaging Biomarkers and AI on Breast Cancer Management: A Brief Review

Breast cancer stands out as the most frequently identified malignancy, ranking as the fifth leading cause of global cancer-related deaths. The American College of Radiology (ACR) introduced the Breast Imaging Reporting and Data System (BI-RADS) as a standard terminology facilitating communication between radiologists and clinicians; however, an update is now imperative to encompass the latest imaging modalities developed subsequent to the 5th edition of BI-RADS. Within this review article, we provide a concise history of BI-RADS, delve into advanced mammography techniques, ultrasonography (US), magnetic resonance imaging (MRI), PET/CT images, and microwave breast imaging, and subsequently furnish comprehensive, updated insights into Molecular Breast Imaging (MBI), diagnostic imaging biomarkers, and the assessment of treatment responses. This endeavor aims to enhance radiologists' proficiency in catering to the personalized needs of breast cancer patients. Lastly, we explore the augmented benefits of artificial intelligence (AI), machine learning (ML), and deep learning (DL) applications in segmenting, detecting, and diagnosing breast cancer, as well as the early prediction of the response of tumors to neoadjuvant chemotherapy (NAC). By assimilating state-of-the-art computer algorithms capable of deciphering intricate imaging data and aiding radiologists in rendering precise and effective diagnoses, AI has profoundly revolutionized the landscape of breast cancer radiology. Its vast potential holds the promise of bolstering radiologists' capabilities and ameliorating patient outcomes in the realm of breast cancer management.

Performance of artificial intelligence in diabetic retinopathy screening: a systematic review and meta-analysis of prospective studies

Aims

To systematically evaluate the diagnostic value of an artificial intelligence (AI) algorithm model for various types of diabetic retinopathy (DR) in prospective studies over the previous five years, and to explore the factors affecting its diagnostic effectiveness.

Materials and methods

A search was conducted in Cochrane Library, Embase, Web of Science, PubMed, and IEEE databases to collect prospective studies on AI models for the diagnosis of DR from January 2017 to December 2022. We used QUADAS-2 to evaluate the risk of bias in the included studies. Meta-analysis was performed using MetaDiSc and STATA 14.0 software to calculate the combined sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of various types of DR. Diagnostic odds ratios, summary receiver operating characteristic (SROC) plots, coupled forest plots, and subgroup analysis were performed according to the DR categories, patient source, region of study, and quality of literature, image, and algorithm.

Results

Finally, 21 studies were included. Meta-analysis showed that the pooled sensitivity, specificity, pooled positive likelihood ratio, pooled negative likelihood ratio, area under the curve, Cochrane Q index, and pooled diagnostic odds ratio of AI model for the diagnosis of DR were 0.880 (0.875-0.884), 0.912 (0.99-0.913), 13.021 (10.738-15.789), 0.083 (0.061-0.112), 0.9798, 0.9388, and 206.80 (124.82-342.63), respectively. The DR categories, patient source, region of study, sample size, quality of literature, image, and algorithm may affect the diagnostic efficiency of AI for DR.

Conclusion

AI model has a clear diagnostic value for DR, but it is influenced by many factors that deserve further study.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42023389687.

A deep learning model established for evaluating lid margin signs with colour anterior segment photography

OBJECTIVES

To evaluate the feasibility of applying a deep learning model to identify lid margin signs from colour anterior segment photography.

METHODS

We collected a total of 832 colour anterior segment photographs from 428 dry eye patients. Eight lid margin signs were labelled by human ophthalmologists. Eight deep learning models were constructed based on VGGNet-13 and trained to identify lid margin signs. Sensitivity, specificity, receiver operative characteristic (ROC) curves and area under the curve (AUC) were applied to evaluate the models.

RESULTS

The AUC for rounding of posterior lid margin was 0.979 and was 0.977 and 0.980 for lid margin irregularity and vascularization. For hyperkeratinization, the AUC was 0.964. The AUCs for meibomian gland orifice (MGO) retroplacement and plugging were 0.963 and 0.968. For the mucocutaneous junction (MCJ) anteroplacement and retroplacement model, the AUCs were 0.950 and 0.978. The sensitivity and specificity for rounding of posterior lid margin were 0.974 and 0.921. For irregularity, the sensitivity and specificity were 0.930 and 0.938, and those for vascularization were 0.923 and 0.961. The hyperkeratinization model achieved a sensitivity and specificity of 0.889 and 0.948. The model identifying MGO plugging and retroplacement achieved a sensitivity of 0.979 and 0.909 with a specificity of 0.867 and 0.967. The sensitivity of MCJ anteroplacement and retroplacement were 0.875/0.969, with a specificity of 0.966/0.888.

CONCLUSIONS

The deep learning model could identify lid margin signs with high sensitivity and specificity. The study provided the potentiality of applying artificial intelligence in lid margin evaluation to assist dry eye decision-making.

Automated machine learning-based classification of proliferative and non-proliferative diabetic retinopathy using optical coherence tomography angiography vascular density maps

PURPOSE

The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm.

METHODS

OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm.

RESULTS

The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR.

CONCLUSIONS

The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps.

Developments in the detection of diabetic retinopathy: a state-of-the-art review of computer-aided diagnosis and machine learning methods

The exponential increase in the number of diabetics around the world has led to an equally large increase in the number of diabetic retinopathy (DR) cases which is one of the major complications caused by diabetes. Left unattended, DR worsens the vision and would lead to partial or complete blindness. As the number of diabetics continue to increase exponentially in the coming years, the number of qualified ophthalmologists need to increase in tandem in order to meet the demand for screening of the growing number of diabetic patients. This makes it pertinent to develop ways to automate the detection process of DR. A computer aided diagnosis system has the potential to significantly reduce the burden currently placed on the ophthalmologists. Hence, this review paper is presented with the aim of summarizing, classifying, and analyzing all the recent development on automated DR detection using fundus images from 2015 up to this date. Such work offers an unprecedentedly thorough review of all the recent works on DR, which will potentially increase the understanding of all the recent studies on automated DR detection, particularly on those that deploys machine learning algorithms. Firstly, in this paper, a comprehensive state-of-the-art review of the methods that have been introduced in the detection of DR is presented, with a focus on machine learning models such as convolutional neural networks (CNN) and artificial neural networks (ANN) and various hybrid models. Each AI will then be classified according to its type (e.g. CNN, ANN, SVM), its specific task(s) in performing DR detection. In particular, the models that deploy CNN will be further analyzed and classified according to some important properties of the respective CNN architectures of each model. A total of 150 research articles related to the aforementioned areas that were published in the recent 5 years have been utilized in this review to provide a comprehensive overview of the latest developments in the detection of DR.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10462-022-10185-6.

Adaptive dynamic analysis-based optical coherence tomography angiography for blood vessel projection artifact suppression

Optical coherence tomography angiography (OCTA) for blood vessel 3-D structure imaging suffers from blood vessel projection artifacts/tail artifacts when using a long decorrelation time (e.g., repeat B-scan acquisition in regular OCTA) or loss of micro vessel signal when using a short decorrelation time. In this work, we developed an adaptive first-order field autocorrelation function (g₁) analysis-based technique to suppress the projection artifacts under macro vessels while enhancing the dynamic signal of micro vessels. The proposed method is based on the differences of the decorrelation rate and the phase variations of g₁ between the vessel voxels and the artifacts regions. A short or long decorrelation time was applied to obtain the dynamic index of the projection artifacts region or the blood vessel region, respectively. Compared to the slab subtraction-based post-image processing-based techniques, the proposed approach addresses this problem on a physical basis and shows the ability to suppress the projection artifacts while enhancing the detection of the micro vessels.

Applications of Artificial Intelligence in Optical Coherence Tomography Angiography Imaging

Optical coherence tomography angiography (OCTA) and artificial intelligence (AI) are two emerging fields that complement each other. OCTA enables the noninvasive, in vivo, 3D visualization of retinal blood flow with a micrometer resolution, which has been impossible with other imaging modalities. As it does not need dye-based injections, it is also a safer procedure for patients. AI has excited great interest in many fields of daily life, by enabling automatic processing of huge amounts of data with a performance that greatly surpasses previous algorithms. It has been used in many breakthrough studies in recent years, such as the finding that AlphaGo can beat humans in the strategic board game of Go. This paper will give a short introduction into both fields and will then explore the manifold applications of AI in OCTA imaging that have been presented in the recent years. These range from signal generation over signal enhancement to interpretation tasks like segmentation and classification. In all these areas, AI-based algorithms have achieved state-of-the-art performance that has the potential to improve standard care in ophthalmology when integrated into the daily clinical routine.

Retinal Structure Detection in OCTA Image via Voting-Based Multitask Learning

Automated detection of retinal structures, such as retinal vessels (RV), the foveal avascular zone (FAZ), and retinal vascular junctions (RVJ), are of great importance for understanding diseases of the eye and clinical decision-making. In this paper, we propose a novel Voting-based Adaptive Feature Fusion multi-task network (VAFF-Net) for joint segmentation, detection, and classification of RV, FAZ, and RVJ in optical coherence tomography angiography (OCTA). A task-specific voting gate module is proposed to adaptively extract and fuse different features for specific tasks at two levels: features at different spatial positions from a single encoder, and features from multiple encoders. In particular, since the complexity of the microvasculature in OCTA images makes simultaneous precise localization and classification of retinal vascular junctions into bifurcation/crossing a challenging task, we specifically design a task head by combining the heatmap regression and grid classification. We take advantage of three different en face angiograms from various retinal layers, rather than following existing methods that use only a single en face. We carry out extensive experiments on three OCTA datasets acquired using different imaging devices, and the results demonstrate that the proposed method performs on the whole better than either the state-of-the-art single-purpose methods or existing multi-task learning solutions. We also demonstrate that our multi-task learning method generalizes across other imaging modalities, such as color fundus photography, and may potentially be used as a general multi-task learning tool. We also construct three datasets for multiple structure detection, and part of these datasets with the source code and evaluation benchmark have been released for public access.

Early Retinal Microvasculopathy in Prediabetic Patients and Correlated Factors

INTRODUCTION

We aimed to detect early retinal microcirculation changes in prediabetic patients and investigate their correlation with clinical examinations.

METHODS

Forty-seven prediabetic individuals, 29 controls, and 81 type 2 diabetic mellitus (T2DM) patients were enrolled in this study. A review of clinical data and spectral-domain optical coherence tomography angiography (SD-OCTA) parameters of macular vessel diameter (VD), foveal avascular zone (FAZ), and macular vessel area density (VAD) was performed.

RESULTS

Levels of low-density lipoprotein cholesterol and triglycerides in prediabetes and T2DM groups were significantly higher than those in the control group. The urine microalbumin-to-creatinine ratio (ACR) was mildly and moderately increased in the prediabetes and T2DM groups, respectively. The estimated glomerular filtration rate of the three groups was within the normal range. SD-OCTA showed that VAD in the superficial macular area was decreased in the prediabetes group compared to the control group (p = 0.01). The FAZ size, particularly in the deep layer, was expanded in the prediabetes group. In the deep retinal layer of the macular area, VD and FAZ size in the prediabetes group were larger than those in the control group. In the prediabetes group, the axial length was significantly correlated with macular VD and FAZ size (p < 0.05), and ACR was correlated with FAZ size (p < 0.05). Age had a negative correlation with VAD (p < 0.01). ACR had a positive correlation with FAZ size (p < 0.05).

CONCLUSIONS

Enlargement and irregularity of the FAZ area, deep capillary dilation, and a decrease in VAD occur in the retina of prediabetic patients with mild kidney function impairment.

Accuracy and feasibility with AI-assisted OCT in retinal disorder community screening

Objective: To evaluate the accuracy and feasibility of the auto-detection of 15 retinal disorders with artificial intelligence (AI)-assisted optical coherence tomography (OCT) in community screening. Methods: A total of 954 eyes of 477 subjects from four local communities were enrolled in this study from September to December 2021. They received OCT scans covering an area of 12 mm × 9 mm at the posterior pole retina involving the macular and optic disc, as well as other ophthalmic examinations performed using their demographic information recorded. The OCT images were analyzed using integrated software with the previously established algorithm based on the deep-learning method and trained to detect 15 kinds of retinal disorders, namely, pigment epithelial detachment (PED), posterior vitreous detachment (PVD), epiretinal membranes (ERMs), sub-retinal fluid (SRF), choroidal neovascularization (CNV), drusen, retinoschisis, cystoid macular edema (CME), exudation, macular hole (MH), retinal detachment (RD), ellipsoid zone disruption, focal choroidal excavation (FCE), choroid atrophy, and retinal hemorrhage. Meanwhile, the diagnosis was also generated from three groups of individual ophthalmologists (group of retina specialists, senior ophthalmologists, and junior ophthalmologists) and compared with those by the AI. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were calculated, and kappa statistics were performed. Results: A total of 878 eyes were finally enrolled, with 76 excluded due to poor image quality. In the detection of 15 retinal disorders, the ROC curve comparison between AI and professors' presented relatively large AUC (0.891-0.997), high sensitivity (87.65-100%), and high specificity (80.12-99.41%). Among the ROC curve comparisons with those by the retina specialists, AI was the closest one to the professors' compared to senior and junior ophthalmologists (p < 0.05). Conclusion: AI-assisted OCT is highly accurate, sensitive, and specific in auto-detection of 15 kinds of retinal disorders, certifying its feasibility and effectiveness in community ophthalmic screening.

Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images

Diabetic retinopathy (DR) is a major health problem that can lead to vision loss if not treated early. In this study, a three-step system for DR detection utilizing optical coherence tomography (OCT) is presented. First, the proposed system segments the retinal layers from the input OCT images. Second, 3D features are extracted from each retinal layer that include the first-order reflectivity and the 3D thickness of the individual OCT layers. Finally, backpropagation neural networks are used to classify OCT images. Experimental studies on 188 cases confirm the advantages of the proposed system over related methods, achieving an accuracy of 96.81%, using the leave-one-subject-out (LOSO) cross-validation. These outcomes show the potential of the suggested method for DR detection using OCT images.

The Role of Medical Image Modalities and AI in the Early Detection, Diagnosis and Grading of Retinal Diseases: A Survey

Traditional dilated ophthalmoscopy can reveal diseases, such as age-related macular degeneration (AMD), diabetic retinopathy (DR), diabetic macular edema (DME), retinal tear, epiretinal membrane, macular hole, retinal detachment, retinitis pigmentosa, retinal vein occlusion (RVO), and retinal artery occlusion (RAO). Among these diseases, AMD and DR are the major causes of progressive vision loss, while the latter is recognized as a world-wide epidemic. Advances in retinal imaging have improved the diagnosis and management of DR and AMD. In this review article, we focus on the variable imaging modalities for accurate diagnosis, early detection, and staging of both AMD and DR. In addition, the role of artificial intelligence (AI) in providing automated detection, diagnosis, and staging of these diseases will be surveyed. Furthermore, current works are summarized and discussed. Finally, projected future trends are outlined. The work done on this survey indicates the effective role of AI in the early detection, diagnosis, and staging of DR and/or AMD. In the future, more AI solutions will be presented that hold promise for clinical applications.

A Self-Supervised Model Advance OCTA Image Disease Diagnosis

Due to the lack of medical image datasets, transfer learning/fine-tuning is generally used to realize disease detection (mainly the ImageNet transfer model). Significant differences of dominance between natural and medical images seriously restrict the performance of the model. In this paper, a contrastive learning method (BY-OCTA) combined with patient metadata is proposed to detect the pathology in fundus OCTA images. This method uses the patient’s metadata to construct positive sample pairs. By introducing super-parameters into the loss function, we can reasonably adjust the approximate proportion of the same patient metadata sample pair, so as to produce a better representation and initialization model. This paper evaluates the performance of downstream tasks by fine-tuning the multi-layer perceptron of the model. Experiments show that the linear model pretrained by BY-OCTA is better than that pretrained by ImageNet and BYOL on multiple datasets. Furthermore, in the case of limited labeled training data, BY-OCTA provides the most significant benefit. This shows that the BY-OCTA pretraining model has better characterization extraction ability and transferability. This method allows a flexible combination of medical opinions and uses metadata to construct positive sample pairs, which can be widely used in medical image interpretation.

The Role of Different Retinal Imaging Modalities in Predicting Progression of Diabetic Retinopathy: A Survey

Diabetic retinopathy (DR) is a devastating condition caused by progressive changes in the retinal microvasculature. It is a leading cause of retinal blindness in people with diabetes. Long periods of uncontrolled blood sugar levels result in endothelial damage, leading to macular edema, altered retinal permeability, retinal ischemia, and neovascularization. In order to facilitate rapid screening and diagnosing, as well as grading of DR, different retinal modalities are utilized. Typically, a computer-aided diagnostic system (CAD) uses retinal images to aid the ophthalmologists in the diagnosis process. These CAD systems use a combination of machine learning (ML) models (e.g., deep learning (DL) approaches) to speed up the diagnosis and grading of DR. In this way, this survey provides a comprehensive overview of different imaging modalities used with ML/DL approaches in the DR diagnosis process. The four imaging modalities that we focused on are fluorescein angiography, fundus photographs, optical coherence tomography (OCT), and OCT angiography (OCTA). In addition, we discuss limitations of the literature that utilizes such modalities for DR diagnosis. In addition, we introduce research gaps and provide suggested solutions for the researchers to resolve. Lastly, we provide a thorough discussion about the challenges and future directions of the current state-of-the-art DL/ML approaches. We also elaborate on how integrating different imaging modalities with the clinical information and demographic data will lead to promising results for the scientists when diagnosing and grading DR. As a result of this article's comparative analysis and discussion, it remains necessary to use DL methods over existing ML models to detect DR in multiple modalities.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Deep Learning Image Analysis of Optical Coherence Tomography Angiography Measured Vessel Density Improves Classification of Healthy and Glaucoma Eyes

PURPOSE

To compare convolutional neural network (CNN) analysis of en face vessel density images to gradient boosting classifier (GBC) analysis of instrument-provided, feature-based optical coherence tomography angiography (OCTA) vessel density measurements and OCT retinal nerve fiber layer (RNFL) thickness measurements for classifying healthy and glaucomatous eyes.

DESIGN

Comparison of diagnostic approaches.

METHODS

A total of 130 eyes of 80 healthy individuals and 275 eyes of 185 glaucoma patients with optic nerve head (ONH) OCTA and OCT imaging were included. Classification performance of a VGG16 CNN trained and tested on entire en face 4.5 × 4.5-mm radial peripapillary capillary OCTA ONH images was compared to the performance of separate GBC models trained and tested on standard OCTA and OCT measurements. Five-fold cross-validation was used to test predictions for CNNs and GBCs. Areas under the precision recall curves (AUPRC) were calculated to control for training/test set size imbalance and were compared.

RESULTS

Adjusted AUPRCs for GBC models were 0.89 (95% CI = 0.82, 0.92) for whole image vessel density GBC, 0.89 (0.83, 0.92) for whole image capillary density GBC, 0.91 (0.88, 0.93) for combined whole image vessel and whole image capillary density GBC, and 0.93 (0.91, 095) for RNFL thickness GBC. The adjusted AUPRC using CNN analysis of en face vessel density images was 0.97 (0.95, 0.99) resulting in significantly improved classification compared to GBC OCTA-based results and GBC OCT-based results (P ≤ 0.01 for all comparisons).

CONCLUSION

Deep learning en face image analysis improves on feature-based GBC models for classifying healthy and glaucoma eyes.

Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age-related macular degeneration

PURPOSE

This study aimed to determine the efficacy of a multimodal deep learning (DL) model using optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) images for the assessment of choroidal neovascularization (CNV) in neovascular age-related macular degeneration (AMD).

METHODS

This retrospective and cross-sectional study was performed at a multicentre, and the inclusion criteria were age >50 years and a diagnosis of typical neovascular AMD. The OCT and OCTA data for an internal data set and two external data sets were collected. A DL model was developed with a novel feature-level fusion (FLF) method utilized to combine the multimodal data. The results were compared with identification performed by an ophthalmologist. The best model was tested on two external data sets to show its potential for clinical use.

RESULTS

Our best model achieved an accuracy of 95.5% and an area under the curve (AUC) of 0.9796 on multimodal data inputs for the internal data set, which is comparable to the performance of retinal specialists. The proposed model reached an accuracy of 100.00% and an AUC of 1.0 for the Ningbo data set, and these performance indicators were 90.48% and an AUC of 0.9727 for the Jinhua data set.

CONCLUSION

The FLF method is feasible and highly accurate, and could enhance the power of the existing computer-aided diagnosis systems. The bi-modal computer-aided diagnosis (CADx) system for the automated identification of CNV activity is an accurate and promising tool in the realm of public health.

A Novel Computer-Aided Diagnostic System for Early Detection of Diabetic Retinopathy Using 3D-OCT Higher-Order Spatial Appearance Model

Early diagnosis of diabetic retinopathy (DR) is of critical importance to suppress severe damage to the retina and/or vision loss. In this study, an optical coherence tomography (OCT)-based computer-aided diagnosis (CAD) method is proposed to detect DR early using structural 3D retinal scans. This system uses prior shape knowledge to automatically segment all retinal layers of the 3D-OCT scans using an adaptive, appearance-based method. After the segmentation step, novel texture features are extracted from the segmented layers of the OCT B-scans volume for DR diagnosis. For every layer, Markov–Gibbs random field (MGRF) model is used to extract the 2nd-order reflectivity. In order to represent the extracted image-derived features, we employ cumulative distribution function (CDF) descriptors. For layer-wise classification in 3D volume, using the extracted Gibbs energy feature, an artificial neural network (ANN) is fed the extracted feature for every layer. Finally, the classification outputs for all twelve layers are fused using a majority voting schema for global subject diagnosis. A cohort of 188 3D-OCT subjects are used for system evaluation using different k-fold validation techniques and different validation metrics. Accuracy of 90.56%, 93.11%, and 96.88% are achieved using 4-, 5-, and 10-fold cross-validation, respectively. Additional comparison with deep learning networks, which represent the state-of-the-art, documented the promise of our system’s ability to diagnose the DR early.

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 the utility of deep learning for predicting therapeutic response in diabetic eye disease

Purpose

Deep learning (DL) is a technique explored within ophthalmology that requires large datasets to distinguish feature representations with high diagnostic performance. There is a need for developing DL approaches to predict therapeutic response, but completed clinical trial datasets are limited in size. Predicting treatment response is more complex than disease diagnosis, where hallmarks of treatment response are subtle. This study seeks to understand the utility of DL for clinical problems in ophthalmology such as predicting treatment response and where large sample sizes for model training are not available.

Materials and Methods

Four DL architectures were trained using cross-validated transfer learning to classify ultra-widefield angiograms (UWFA) and fluid-compartmentalized optical coherence tomography (OCT) images from a completed clinical trial (PERMEATE) dataset (n=29) as tolerating or requiring extended interval Anti-VEGF dosing. UWFA images (n=217) from the Anti-VEGF study were divided into five increasingly larger subsets to evaluate the influence of dataset size on performance. Class activation maps (CAMs) were generated to identify regions of model attention.

Results

The best performing DL model had a mean AUC of 0.507 ± 0.042 on UWFA images, and highest observed AUC of 0.503 for fluid-compartmentalized OCT images. DL had a best performing AUC of 0.634 when dataset size was incrementally increased. Resulting CAMs show inconsistent regions of interest.

Conclusions

This study demonstrated the limitations of DL for predicting therapeutic response when large datasets were not available for model training. Our findings suggest the need for hand-crafted approaches for complex and data scarce prediction problems in ophthalmology.

Optical Coherence Tomography Angiography in Diabetic Patients: A Systematic Review

Background: Diabetic retinopathy (DR) is the leading cause of legal blindness in the working population in developed countries. Optical coherence tomography (OCT) angiography (OCTA) has risen as an essential tool in the diagnosis and control of diabetic patients, with and without DR, allowing visualisation of the retinal and choroidal microvasculature, their qualitative and quantitative changes, the progression of vascular disease, quantification of ischaemic areas, and the detection of preclinical changes. The aim of this article is to analyse the current applications of OCTA and provide an updated overview of them in the evaluation of DR. Methods: A systematic literature search was performed in PubMed and Embase, including the keywords “OCTA” OR “OCT angiography” OR “optical coherence tomography angiography” AND “diabetes” OR “diabetes mellitus” OR “diabetic retinopathy” OR “diabetic maculopathy” OR “diabetic macular oedema” OR “diabetic macular ischaemia”. Of the 1456 studies initially identified, 107 studies were screened after duplication, and those articles that did not meet the selection criteria were removed. Finally, after looking for missing data, we included 135 studies in this review. Results: We present the common and distinctive findings in the analysed papers after the literature search including the diagnostic use of OCTA in diabetes mellitus (DM) patients. We describe previous findings in retinal vascularization, including microaneurysms, foveal avascular zone (FAZ) changes in both size and morphology, changes in vascular perfusion, the appearance of retinal microvascular abnormalities or new vessels, and diabetic macular oedema (DME) and the use of deep learning technology applied to this disease. Conclusion: OCTA findings enable the diagnosis and follow-up of DM patients, including those with no detectable lesions with other devices. The evaluation of retinal and choroidal plexuses using OCTA is a fundamental tool for the diagnosis and prognosis of DR.

Role of Optical Coherence Tomography Imaging in Predicting Progression of Age-Related Macular Disease: A Survey

In developed countries, age-related macular degeneration (AMD), a retinal disease, is the main cause of vision loss in the elderly. Optical Coherence Tomography (OCT) is currently the gold standard for assessing individuals for initial AMD diagnosis. In this paper, we look at how OCT imaging can be used to diagnose AMD. Our main aim is to examine and compare automated computer-aided diagnostic (CAD) systems for diagnosing and grading of AMD. We provide a brief summary, outlining the main aspects of performance assessment and providing a basis for current research in AMD diagnosis. As a result, the only viable alternative is to prevent AMD and stop both this devastating eye condition and unwanted visual impairment. On the other hand, the grading of AMD is very important in order to detect early AMD and prevent patients from reaching advanced AMD disease. In light of this, we explore the remaining issues with automated systems for AMD detection based on OCT imaging, as well as potential directions for diagnosis and monitoring systems based on OCT imaging and telemedicine applications.

A deep learning model for identifying diabetic retinopathy using optical coherence tomography angiography

As the prevalence of diabetes increases, millions of people need to be screened for diabetic retinopathy (DR). Remarkable advances in technology have made it possible to use artificial intelligence to screen DR from retinal images with high accuracy and reliability, resulting in reducing human labor by processing large amounts of data in a shorter time. We developed a fully automated classification algorithm to diagnose DR and identify referable status using optical coherence tomography angiography (OCTA) images with convolutional neural network (CNN) model and verified its feasibility by comparing its performance with that of conventional machine learning model. Ground truths for classifications were made based on ultra-widefield fluorescein angiography to increase the accuracy of data annotation. The proposed CNN classifier achieved an accuracy of 91–98%, a sensitivity of 86–97%, a specificity of 94–99%, and an area under the curve of 0.919–0.976. In the external validation, overall similar performances were also achieved. The results were similar regardless of the size and depth of the OCTA images, indicating that DR could be satisfactorily classified even with images comprising narrow area of the macular region and a single image slab of retina. The CNN-based classification using OCTA is expected to create a novel diagnostic workflow for DR detection and referral.

Artificial intelligence in OCT angiography

Optical coherence tomographic angiography (OCTA) is a non-invasive imaging modality that provides three-dimensional, information-rich vascular images. With numerous studies demonstrating unique capabilities in biomarker quantification, diagnosis, and monitoring, OCTA technology has seen rapid adoption in research and clinical settings. The value of OCTA imaging is significantly enhanced by image analysis tools that provide rapid and accurate quantification of vascular features and pathology. Today, the most powerful image analysis methods are based on artificial intelligence (AI). While AI encompasses a large variety of techniques, machine-learning-based, and especially deep-learning-based, image analysis provides accurate measurements in a variety of contexts, including different diseases and regions of the eye. Here, we discuss the principles of both OCTA and AI that make their combination capable of answering new questions. We also review contemporary applications of AI in OCTA, which include accurate detection of pathologies such as choroidal neovascularization, precise quantification of retinal perfusion, and reliable disease diagnosis.

Spotlight-based 3D Instrument Guidance for Retinal Surgery

Retinal surgery is a complex activity that can be challenging for a surgeon to perform effectively and safely. Image guided robot-assisted surgery is one of the promising solutions that bring significant surgical enhancement in treatment outcome and reduce the physical limitations of human surgeons. In this paper, we demonstrate a novel method for 3D guidance of the instrument based on the projection of spotlight in the single microscope images. The spotlight projection mechanism is firstly analyzed and modeled with a projection on both a plane and a sphere surface. To test the feasibility of the proposed method, a light fiber is integrated into the instrument which is driven by the Steady-Hand Eye Robot (SHER). The spot of light is segmented and tracked on a phantom retina using the proposed algorithm. The static calibration and dynamic test results both show that the proposed method can easily archive 0.5 mm of tip-to-surface distance which is within the clinically acceptable accuracy for intraocular visual guidance.

Automated Detection and Diagnosis of Diabetic Retinopathy: A Comprehensive Survey

Diabetic Retinopathy (DR) is a leading cause of vision loss in the world. In the past few years, artificial intelligence (AI) based approaches have been used to detect and grade DR. Early detection enables appropriate treatment and thus prevents vision loss. For this purpose, both fundus and optical coherence tomography (OCT) images are used to image the retina. Next, Deep-learning (DL)-/machine-learning (ML)-based approaches make it possible to extract features from the images and to detect the presence of DR, grade its severity and segment associated lesions. This review covers the literature dealing with AI approaches to DR such as ML and DL in classification and segmentation that have been published in the open literature within six years (2016-2021). In addition, a comprehensive list of available DR datasets is reported. This list was constructed using both the PICO (P-Patient, I-Intervention, C-Control, O-Outcome) and Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) 2009 search strategies. We summarize a total of 114 published articles which conformed to the scope of the review. In addition, a list of 43 major datasets is presented.

Effect of Patient Clinical Variables in Osteoporosis Classification Using Hip X-rays in Deep Learning Analysis

Background and Objectives: A few deep learning studies have reported that combining image features with patient variables enhanced identification accuracy compared with image-only models. However, previous studies have not statistically reported the additional effect of patient variables on the image-only models. This study aimed to statistically evaluate the osteoporosis identification ability of deep learning by combining hip radiographs with patient variables. Materials andMethods: We collected a dataset containing 1699 images from patients who underwent skeletal-bone-mineral density measurements and hip radiography at a general hospital from 2014 to 2021. Osteoporosis was assessed from hip radiographs using convolutional neural network (CNN) models (ResNet18, 34, 50, 101, and 152). We also investigated ensemble models with patient clinical variables added to each CNN. Accuracy, precision, recall, specificity, F1 score, and area under the curve (AUC) were calculated as performance metrics. Furthermore, we statistically compared the accuracy of the image-only model with that of an ensemble model that included images plus patient factors, including effect size for each performance metric. Results: All metrics were improved in the ResNet34 ensemble model compared with the image-only model. The AUC score in the ensemble model was significantly improved compared with the image-only model (difference 0.004; 95% CI 0.002–0.0007; p = 0.0004, effect size: 0.871). Conclusions: This study revealed the additional effect of patient variables in identification of osteoporosis using deep CNNs with hip radiographs. Our results provided evidence that the patient variables had additive synergistic effects on the image in osteoporosis identification.

Machine learning in optical coherence tomography angiography

Optical coherence tomography angiography (OCTA) offers a noninvasive label-free solution for imaging retinal vasculatures at the capillary level resolution. In principle, improved resolution implies a better chance to reveal subtle microvascular distortions associated with eye diseases that are asymptomatic in early stages. However, massive screening requires experienced clinicians to manually examine retinal images, which may result in human error and hinder objective screening. Recently, quantitative OCTA features have been developed to standardize and document retinal vascular changes. The feasibility of using quantitative OCTA features for machine learning classification of different retinopathies has been demonstrated. Deep learning-based applications have also been explored for automatic OCTA image analysis and disease classification. In this article, we summarize recent developments of quantitative OCTA features, machine learning image analysis, and classification.

Association between smoking history and optical coherence tomography angiography findings in diabetic patients without diabetic retinopathy

Purpose

To investigate any associations between cigarette smoking and retinal microvascular changes in diabetic patients without visible retinopathy.

Design

Retrospective, cross-sectional study.

Participants

1099 eyes from 1099 diabetic patients with no clinical evidence of diabetic retinopathy (DR) were included in this study.

Methods

Diabetic patients underwent optical coherence tomography angiography (OCTA) scanning at Zuckerberg San Francisco General Hospital and Trauma Center between April 2018 and September 2019. Patient demographic and clinical information was collected. Standard bivariate statistics and multivariate linear regression were performed.

Main outcome measures

OCTA parameters included metrics related to the foveal avascular zone (FAZ; area, perimeter, circularity), perfusion density (PD; full, center, inner), and vessel length density (VLD; full, center, inner).

Results

The study population included 750 non-smokers and 349 smokers. FAZ perimeter was the only OCTA parameter that was significantly different between the two groups on uncontrolled analysis (P = 0.033). Multivariate regression analyses revealed significant associations between lower VLD full (β = -0.31, P = 0.048), lower VLD inner (β = -0.35, P = 0.046) and a history of smoking. No significant associations between cigarette smoking and either FAZ or PD were detected.

Conclusions

Our results suggest that smoking is likely associated with deleterious changes in the retinal microvasculature of patients with a history of diabetes and no visible DR. Based on these findings, diabetic patients with a history of smoking may benefit from higher prioritization in terms of ophthalmic screening.

Retinal Microvascular Vessel Density Differences between Adult Athletes and Nonathletes

SIGNIFICANCE

Regular physical activity may affect the neurovascular structures. Many studies have shown the positive effects of physical activity on ocular disorders such as glaucoma, retinopathy, and macular degeneration. Athletes were expected to have a better retinal vascular structure compared with the nonathletes.

PURPOSE

This study aimed to evaluate the effects of regular physical activity on the retinal microvascular structure.

METHODS

This observational and cross-sectional study was conducted between January and July 2020 with participants aged 20 to 35 years who had a visual acuity of ≥20/20, axial length of 22 to 24 mm, refractive defect spherical equivalent of ≤±1 D, and IOP of ≤21 mmHg. Updated AngioScan software (Navis version 1.8.0) of Nidek's RS-3000 Advance system was used to analyze the spectral-domain optical coherence tomography and optical coherence tomography angiography images.

RESULTS

A total of 60 right eyes of 60 individuals were included in the study. Thirty subjects were in the athlete group, and 30 patients were in the nonathlete group. Sixteen of the individuals in the athlete group and 15 in the nonathlete group were women (P > .05). Retinal nerve fiber layer and ganglion cell complex thicknesses in all quadrants were thinner in nonathletes (P < .05). All of the Early Treatment Diabetic Retinopathy Study regions except central foveal subfield thickness were significantly higher in the athlete group (P < .05). In the nonathlete group, significantly reduced vessel densities of the superficial and deep capillary plexus and radial peripapillary capillary plexus, and the foveal avascular zone circularity index along with an increased foveal avascular zone perimeter and area were also detected (P < .05).

CONCLUSIONS

Our study revealed that optical coherence tomography angiography measurements may be used in the determination of the effects of physical activity on retinal vascular structure changes.

Deep learning differentiates between healthy and diabetic mouse ears from optical coherence tomography angiography images

We trained a deep learning algorithm to use skin optical coherence tomography (OCT) angiograms to differentiate between healthy and type 2 diabetic mice. OCT angiograms were acquired with a custom‐built OCT system based on an akinetic swept laser at 1322 nm with a lateral resolution of ∼13 μm and using split‐spectrum amplitude decorrelation. Our data set consisted of 24 stitched angiograms of the full ear, with a size of approximately 8.2 × 8.2 mm, evenly distributed between healthy and diabetic mice. The deep learning classification algorithm uses the ResNet v2 convolutional neural network architecture and was trained on small patches extracted from the full ear angiograms. For individual patches, we obtained a cross‐validated accuracy of 0.925 and an area under the receiver operating characteristic curve (ROC AUC) of 0.974. Averaging over multiple patches extracted from each ear resulted in the correct classification of all 24 ears.

Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images

This study proposes a novel computer assisted diagnostic (CAD) system for early diagnosis of diabetic retinopathy (DR) using optical coherence tomography (OCT) B-scans. The CAD system is based on fusing novel OCT markers that describe both the morphology/anatomy and the reflectivity of retinal layers to improve DR diagnosis. This system separates retinal layers automatically using a segmentation approach based on an adaptive appearance and their prior shape information. High-order morphological and novel reflectivity markers are extracted from individual segmented layers. Namely, the morphological markers are layer thickness and tortuosity while the reflectivity markers are the 1st-order reflectivity of the layer in addition to local and global high-order reflectivity based on Markov-Gibbs random field (MGRF) and gray-level co-occurrence matrix (GLCM), respectively. The extracted image-derived markers are represented using cumulative distribution function (CDF) descriptors. The constructed CDFs are then described using their statistical measures, i.e., the 10th through 90th percentiles with a 10% increment. For individual layer classification, each extracted descriptor of a given layer is fed to a support vector machine (SVM) classifier with a linear kernel. The results of the four classifiers are then fused using a backpropagation neural network (BNN) to diagnose each retinal layer. For global subject diagnosis, classification outputs (probabilities) of the twelve layers are fused using another BNN to make the final diagnosis of the B-scan. This system is validated and tested on 130 patients, with two scans for both eyes (i.e. 260 OCT images), with a balanced number of normal and DR subjects using different validation metrics: 2-folds, 4-folds, 10-folds, and leave-one-subject-out (LOSO) cross-validation approaches. The performance of the proposed system was evaluated using sensitivity, specificity, F1-score, and accuracy metrics. The system's performance after the fusion of these different markers showed better performance compared with individual markers and other machine learning fusion methods. Namely, it achieved [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively, using the LOSO cross-validation technique. The reported results, based on the integration of morphology and reflectivity markers and by using state-of-the-art machine learning classifications, demonstrate the ability of the proposed system to diagnose the DR early.

Effects of Induced Astigmatism on Spectral Domain-OCT Angiography Quantitative Metrics

PURPOSE

To analyze the effect of induced astigmatism on en-face spectral-domain optical coherence tomography angiography quantitative metrics.

DESIGN

Prospective crossover study.

METHODS

Normal eyes without astigmatism and with 0.75, 1.75, and 2.75 diopters (D) of with-the-rule (WTR) astigmatism were imaged using a 3 × 3-mm scan pattern SD-OCTA CIRRUS 5000 HD-OCT with AngioPlex (Carl Zeiss Meditec, Dublin, CA, USA). Quantitative parameters, including foveal avascular zone metrics, parafoveal vessel length density (VD), and perfusion density (PD) were corrected for magnification secondary to axial length and analyzed. Univariate linear regressions were performed within each eye to correlate quantitative metrics to the level of an induced astigmatic cylinder.

RESULTS

Fifteen eyes from 15 patients were imaged. Every 1-D increase in induced WTR astigmatism was associated with a statistically significant decrease in VD and PD within all Early Treatment Diabetic Retinopathy Study inner ring quadrants; however, especially more so nasally (VD: 0.63; P < .001; PD: 0.0089; P = .001). For every 1-D increase in induced astigmatism, the resulting decrease in the inner ring superior quadrant was 12% greater for VD and 16% greater for PD versus that in the inferior quadrant. The resulting decrease in the inner ring nasal quadrant was 40% greater for VD and 48% greater for PD versus that in the temporal quadrant.

CONCLUSIONS

Increasing levels of induced WTR astigmatism correlated with globally diminishing VD and PD, was more symmetrical for vertical than horizontal quadrants, and was most pronounced nasally. This may be due to a high prevalence of horizontally oriented vessels nasally and the horizontal optical defocus induced by WTR astigmatism.

Model-to-Data Approach for Deep Learning in Optical Coherence Tomography Intraretinal Fluid Segmentation

Importance

Amid an explosion of interest in deep learning in medicine, including within ophthalmology, concerns regarding data privacy, security, and sharing are of increasing importance. A model-to-data approach, in which the model itself is transferred rather than data, can circumvent many of these challenges but has not been previously demonstrated in ophthalmology.

Objective

To determine whether a model-to-data deep learning approach (ie, validation of the algorithm without any data transfer) can be applied in ophthalmology.

Design, Setting, and Participants

This single-center cross-sectional study included patients with active exudative age-related macular degeneration undergoing optical coherence tomography (OCT) at the New England Eye Center from August 1, 2018, to February 28, 2019. Data were primarily analyzed from March 1 to June 20, 2019.

Main Outcomes and Measures

Training of the deep learning model, using a model-to-data approach, in recognizing intraretinal fluid (IRF) on OCT B-scans.

Results

The model was trained (learning curve Dice coefficient, >80%) using 400 OCT B-scans from 128 participants (69 female [54%] and 59 male [46%]; mean [SD] age, 77.5 [9.1] years). In comparing the model with manual human grading of IRF pockets, no statistically significant difference in Dice coefficients or intersection over union scores was found (P > .05).

Conclusions and Relevance

A model-to-data approach to deep learning applied in ophthalmology avoided many of the traditional hurdles in large-scale deep learning, including data sharing, security, and privacy concerns. Although the clinical relevance of these results is limited at this time, this proof-of-concept study suggests that such a paradigm should be further examined in larger-scale, multicenter deep learning studies.

Evaluation of microvascular changes in retinal zones and optic disc in pediatric patients with type 1 diabetes mellitus

PURPOSE

The objective of this study was to evaluate the vascular parameters of the retinal zones and the optic disc (OD) with the use of optical coherence tomography angiography (OCTA) in pediatric patients with type 1 diabetes mellitus (T1DM).

METHODS

This study enrolled 60 patients with T1DM without clinically detectable diabetic retinopathy (DR), along with 59 age-, gender-, and pubertal stage-matched controls. The ages of the participants in both groups were < 18 years. Retinal and OD measurements were carried out with OCTA. Foveal avascular zone (FAZ) area, non-flow area (NFA), FAZ perimeter (PERIM), acircularity index of FAZ (AI, the rate of the perimeter of FAZ and the perimeter of a circle with equal area), foveal density (FD), superficial (SCP), and the deep capillary plexus (DCP) were analyzed in the macular region. SCP and DCP were also scanned centered on the OD. Correlations between the OCTA parameters with duration of DM, glycated hemoglobin (HbA1c) levels, and microalbuminuria were evaluated among patients with T1DM.

RESULTS

The mean values for NFA were significantly higher and mean FD were significantly lower in the diabetic group compared with the controls (p = 0.02 and p = 0.01, respectively). The mean values for SCP and DCP were significantly lower in diabetic group (p < 0.05). The mean values for capillary density in the OD were also significantly lower in diabetic group (p < 0.05). There were correlations between the duration of T1DM, HbA1c levels and microalbuminuria, and the investigated parameters of OCTA.

CONCLUSIONS

The presence of microvascular changes in both retinal zones and the OD in children with T1DM without retinopathy is an important data. OCTA can be used for the early detection of DR in children.

Nomogram-Based Prediction of the Risk of Diabetic Retinopathy: A Retrospective Study

OBJECTIVES

This study is aimed at developing a risk nomogram of diabetic retinopathy (DR) in a Chinese population with type 2 diabetes mellitus (T2DM).

METHODS

A questionnaire survey, biochemical indicator examination, and physical examination were performed on 4170 T2DM patients, and the collected data were used to evaluate the DR risk in T2DM patients. By operating R software, firstly, the least absolute shrinkage and selection operator (LASSO) regression analysis was used to optimize variable selection by running cyclic coordinate descent with 10 times K cross-validation. Secondly, multivariable logistic regression analysis was applied to build a predicting model introducing the predictors selected from the LASSO regression analysis. The nomogram was developed based on the selected variables visually. Thirdly, calibration plot, receiver operating characteristic (ROC) curve, and decision curve analysis were used to validate the model, and further assessment was running by external validation.

RESULTS

Seven predictors were selected by LASSO from 19 variables, including age, course of disease, postprandial blood glucose (PBG), glycosylated haemoglobin A1c (HbA1c), uric creatinine (UCR), urinary microalbumin (UMA), and systolic blood pressure (SBP). The model built by these 7 predictors displayed medium prediction ability with the area under the ROC curve of 0.700 in the training set and 0.715 in the validation set. The decision curve analysis curve showed that the nomogram could be applied clinically if the risk threshold is between 21% and 57% and 21%-51% in external validation.

CONCLUSION

Introducing age, course of disease, PBG, HbA1c, UCR, UMA, and SBP, the risk nomogram is useful for prediction of DR risk in T2DM individuals.

The Application of Optical Coherence Tomography Angiography in Cerebral Small Vessel Disease, Ischemic Stroke, and Dementia: A Systematic Review

Objective: To investigate the application of optical coherence tomography angiography (OCTA) in cerebral small vessel disease (SVD), ischemic stroke and dementia. Methods: We conducted a systematic search in MEDLINE (from inception) and EMBASE (from 1980) to end 2019 for human studies that measured retinal parameters in cerebral SVD, ischemic stroke, and dementia using OCTA. Results: Fourteen articles (n = 989) provided relevant data. Ten studies included patients with Alzheimer disease (AD) and mild cognitive impairment (n = 679), two investigated pre-symptomatic AD participants (n = 154), and two investigated monogenic SVD patients with cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (n = 32) and Fabry disease (n = 124). Methods to reduce bias and risk factor adjustment were poorly reported. Substantial methodological variations between studies precluded a formal meta-analysis. Quantitative measurements revealed significant yet inconclusive changes in foveal avascular zone, perfusion density, and vessel density (VD) in AD, presymptomatic AD, and SVD patients. Two (n = 160) of three studies (n = 192) showed association between decreased VD and increased white matter hyperintensities. In three (n = 297) of seven studies (n = 563), better cognitive function was associated with increased VD. One study (n = 52) suggested increased VD was associated with increased ganglion cell-inner plexiform layer thickness in AD yet with no covariate adjustment. Conclusions: Changes in retinal microvasculature identified using OCTA are associated with monogenic SVD and different stages of AD, but data are limited and partly confounded by methodological differences. Larger studies with risk factors adjustment and more consistent OCTA methods are needed to fully exploit this technology. PROSPERO registration number: CRD42020166929.