Automated retinal image quality assessment on the UK Biobank dataset for epidemiological studies

Standardization and clinical applications of retinal imaging biomarkers for cardiovascular disease: a Roadmap from an NHLBI workshop

The accessibility of the retina with the use of non-invasive and relatively low-cost ophthalmic imaging techniques and analytics provides a unique opportunity to improve the detection, diagnosis and monitoring of systemic diseases. The National Heart, Lung, and Blood Institute conducted a workshop in October 2022 to examine this concept. On the basis of the discussions at that workshop, this Roadmap describes current knowledge gaps and new research opportunities to evaluate the relationships between the eye (in particular, retinal biomarkers) and the risk of cardiovascular diseases, including coronary artery disease, heart failure, stroke, hypertension and vascular dementia. Identified gaps include the need to simplify and standardize the capture of high-quality images of the eye by non-ophthalmic health workers and to conduct longitudinal studies using multidisciplinary networks of diverse at-risk populations with improved implementation and methods to protect participant and dataset privacy. Other gaps include improving the measurement of structural and functional retinal biomarkers, determining the relationship between microvascular and macrovascular risk factors, improving multimodal imaging 'pipelines', and integrating advanced imaging with 'omics', lifestyle factors, primary care data and radiological reports, by using artificial intelligence technology to improve the identification of individual-level risk. Future research on retinal microvascular disease and retinal biomarkers might additionally provide insights into the temporal development of microvascular disease across other systemic vascular beds.

Automated analysis of vessel morphometry in retinal images from a Danish high street optician setting

PURPOSE

To evaluate the test performance of the QUARTZ (QUantitative Analysis of Retinal vessel Topology and siZe) software in detecting retinal features from retinal images captured by health care professionals in a Danish high street optician chain, compared with test performance from other large population studies (i.e., UK Biobank) where retinal images were captured by non-experts.

METHOD

The dataset FOREVERP (Finding Ophthalmic Risk and Evaluating the Value of Eye exams and their predictive Reliability, Pilot) contains retinal images obtained from a Danish high street optician chain. The QUARTZ algorithm utilizes both image processing and machine learning methods to determine retinal image quality, vessel segmentation, vessel width, vessel classification (arterioles or venules), and optic disc localization. Outcomes were evaluated by metrics including sensitivity, specificity, and accuracy and compared to human expert ground truths.

RESULTS

QUARTZ's performance was evaluated on a subset of 3,682 images from the FOREVERP database. 80.55% of the FOREVERP images were labelled as being of adequate quality compared to 71.53% of UK Biobank images, with a vessel segmentation sensitivity of 74.64% and specificity of 98.41% (FOREVERP) compared with a sensitivity of 69.12% and specificity of 98.88% (UK Biobank). The mean (± standard deviation) vessel width of the ground truth was 16.21 (4.73) pixels compared to that predicted by QUARTZ of 17.01 (4.49) pixels, resulting in a difference of -0.8 (1.96) pixels. The differences were stable across a range of vessels. The detection rate for optic disc localisation was similar for the two datasets.

CONCLUSION

QUARTZ showed high performance when evaluated on the FOREVERP dataset, and demonstrated robustness across datasets, providing validity to direct comparisons and pooling of retinal feature measures across data sources.

A narrative review of retinal vascular parameters and the applications (Part I): Measuring methods

The retina is often used to evaluate the vascular health status of eyes and the whole body directly and noninvasively in vivo. Retinal vascular parameters included caliber, tortuosity and fractal dimension. These variables represent the density or geometric characteristics of the vascular network apart from reflecting structural changes in the retinal vessel system. Currently, these parameters are often used as indicators of retinal disease, cardiovascular and cerebrovascular disease. Advanced digital fundus photography apparatus and computer-assisted analysis techniques combined with artificial intelligence, make the quantitative calculation of these parameters easier, objective, and labor-saving.

Cohort profile: rationale and methods of UK Biobank repeat imaging study eye measures to study dementia

PURPOSE

The retina provides biomarkers of neuronal and vascular health that offer promising insights into cognitive ageing, mild cognitive impairment and dementia. This article described the rationale and methodology of eye and vision assessments with the aim of supporting the study of dementia in the UK Biobank Repeat Imaging study.

PARTICIPANTS

UK Biobank is a large-scale, multicentre, prospective cohort containing in-depth genetic, lifestyle, environmental and health information from half a million participants aged 40-69 enrolled in 2006-2010 across the UK. A subset (up to 60 000 participants) of the cohort will be invited to the UK Biobank Repeat Imaging Study to collect repeated brain, cardiac and abdominal MRI scans, whole-body dual-energy X-ray absorptiometry, carotid ultrasound, as well as retinal optical coherence tomography (OCT) and colour fundus photographs.

FINDINGS TO DATE

UK Biobank has helped make significant advances in understanding risk factors for many common diseases, including for dementia and cognitive decline. Ophthalmic genetic and epidemiology studies have also benefited from the unparalleled combination of very large numbers of participants, deep phenotyping and longitudinal follow-up of the cohort, with comprehensive health data linkage to disease outcomes. In addition, we have used UK Biobank data to describe the relationship between retinal structures, cognitive function and brain MRI-derived phenotypes.

FUTURE PLANS

The collection of eye-related data (eg, OCT), as part of the UK Biobank Repeat Imaging study, will take place in 2022-2028. The depth and breadth and longitudinal nature of this dataset, coupled with its open-access policy, will create a major new resource for dementia diagnostic discovery and to better understand its association with comorbid diseases. In addition, the broad and diverse data available in this study will support research into ophthalmic diseases and various other health outcomes beyond dementia.

Fine-mapping of retinal vascular complexity loci identifies Notch regulation as a shared mechanism with myocardial infarction outcomes

There is increasing evidence that the complexity of the retinal vasculature measured as fractal dimension, Df, might offer earlier insights into the progression of coronary artery disease (CAD) before traditional biomarkers can be detected. This association could be partly explained by a common genetic basis; however, the genetic component of Df is poorly understood. We present a genome-wide association study (GWAS) of 38,000 individuals with white British ancestry from the UK Biobank aimed to comprehensively study the genetic component of Df and analyse its relationship with CAD. We replicated 5 Df loci and found 4 additional loci with suggestive significance (P < 1e-05) to contribute to Df variation, which previously were reported in retinal tortuosity and complexity, hypertension, and CAD studies. Significant negative genetic correlation estimates support the inverse relationship between Df and CAD, and between Df and myocardial infarction (MI), one of CAD's fatal outcomes. Fine-mapping of Df loci revealed Notch signalling regulatory variants supporting a shared mechanism with MI outcomes. We developed a predictive model for MI incident cases, recorded over a 10-year period following clinical and ophthalmic evaluation, combining clinical information, Df, and a CAD polygenic risk score. Internal cross-validation demonstrated a considerable improvement in the area under the curve (AUC) of our predictive model (AUC = 0.770 ± 0.001) when comparing with an established risk model, SCORE, (AUC = 0.741 ± 0.002) and extensions thereof leveraging the PRS (AUC = 0.728 ± 0.001). This evidences that Df provides risk information beyond demographic, lifestyle, and genetic risk factors. Our findings shed new light on the genetic basis of Df, unveiling a common control with MI, and highlighting the benefits of its application in individualised MI risk prediction.

GWAS on retinal vasculometry phenotypes

The eye is the window through which light is transmitted and visual sensory signalling originates. It is also a window through which elements of the cardiovascular and nervous systems can be directly inspected, using ophthalmoscopy or retinal imaging. Measurements of ocular parameters may therefore offer important information on the physiology and homeostasis of these two important systems. Here we report the results of a genetic characterisation of retinal vasculature. Four genome-wide association studies performed on different aspects of retinal vasculometry phenotypes, such as arteriolar and venular tortuosity and width, found significant similarities between retinal vascular characteristics and cardiometabolic health. Our analyses identified 119 different regions of association with traits of retinal vasculature, including 89 loci associated arteriolar tortuosity, the strongest of which was rs35131825 (p = 2.00×10-108), 2 loci with arteriolar width (rs12969347, p = 3.30×10-09 and rs5442, p = 1.9E-15), 17 other loci associated with venular tortuosity and 11 novel associations with venular width. Our causal inference analyses also found that factors linked to arteriolar tortuosity cause elevated diastolic blood pressure and not vice versa.

EfficientNetV2 Based Ensemble Model for Quality Estimation of Diabetic Retinopathy Images from DeepDRiD

Diabetic retinopathy (DR) is one of the major complications caused by diabetes and is usually identified from retinal fundus images. Screening of DR from digital fundus images could be time-consuming and error-prone for ophthalmologists. For efficient DR screening, good quality of the fundus image is essential and thereby reduces diagnostic errors. Hence, in this work, an automated method for quality estimation (QE) of digital fundus images using an ensemble of recent state-of-the-art EfficientNetV2 deep neural network models is proposed. The ensemble method was cross-validated and tested on one of the largest openly available datasets, the Deep Diabetic Retinopathy Image Dataset (DeepDRiD). We obtained a test accuracy of 75% for the QE, outperforming the existing methods on the DeepDRiD. Hence, the proposed ensemble method may be a potential tool for automated QE of fundus images and could be handy to ophthalmologists.

Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke

AIMS

We examine whether inclusion of artificial intelligence (AI)-enabled retinal vasculometry (RV) improves existing risk algorithms for incident stroke, myocardial infarction (MI) and circulatory mortality.

METHODS

AI-enabled retinal vessel image analysis processed images from 88 052 UK Biobank (UKB) participants (aged 40-69 years at image capture) and 7411 European Prospective Investigation into Cancer (EPIC)-Norfolk participants (aged 48-92). Retinal arteriolar and venular width, tortuosity and area were extracted. Prediction models were developed in UKB using multivariable Cox proportional hazards regression for circulatory mortality, incident stroke and MI, and externally validated in EPIC-Norfolk. Model performance was assessed using optimism adjusted calibration, C-statistics and R² statistics. Performance of Framingham risk scores (FRS) for incident stroke and incident MI, with addition of RV to FRS, were compared with a simpler model based on RV, age, smoking status and medical history (antihypertensive/cholesterol lowering medication, diabetes, prevalent stroke/MI).

RESULTS

UKB prognostic models were developed on 65 144 participants (mean age 56.8; median follow-up 7.7 years) and validated in 5862 EPIC-Norfolk participants (67.6, 9.1 years, respectively). Prediction models for circulatory mortality in men and women had optimism adjusted C-statistics and R² statistics between 0.75-0.77 and 0.33-0.44, respectively. For incident stroke and MI, addition of RV to FRS did not improve model performance in either cohort. However, the simpler RV model performed equally or better than FRS.

CONCLUSION

RV offers an alternative predictive biomarker to traditional risk-scores for vascular health, without the need for blood sampling or blood pressure measurement. Further work is needed to examine RV in population screening to triage individuals at high-risk.

Retinal microvascular associations with cardiometabolic risk factors differ by diabetes status: results from the UK Biobank

AIMS/HYPOTHESIS

The aim of the study was to examine the association of retinal vessel morphometry with BP, body composition and biochemistry, and to determine whether these associations differ by diabetes status.

METHODS

The UK Biobank ocular assessment included 68,550 participants aged 40-70 years who underwent non-mydriatic retinal photography, BP and body composition measurements, and haematological analysis. A fully automated image analysis program provided measurements of retinal vessel diameter and tortuosity. The associations between retinal vessel morphology and cardiometabolic risk factors by diabetes status were examined using multilevel linear regression, to provide absolute differences in vessel diameter and percentage differences in tortuosity (allowing for within-person clustering).

RESULTS

A total of 50,233 participants (a reduction from 68,550) were included in these analyses. Overall, those with diabetes had significantly more tortuous venules and wider arteriolar diameters compared with those without. Associations between venular tortuosity and cardiometabolic risk factors differed according to diabetes status (p interaction <0.01) for total fat mass index, HbA_1c, C-reactive protein, white cell count and granulocyte count. For example, a unit rise in white cell count was associated with a 0.18% increase (95% CI 0.05, 0.32%) in venular tortuosity for those without diabetes and a 1.48% increase (95% CI 0.90, 2.07%) among those with diabetes. For arteriolar diameter, significant interactions were evident for systolic BP, diastolic BP, mean arterial pressure (MAP) and LDL-cholesterol. For example, a 10 mmHg rise in systolic BP was associated with a -0.92 μm difference (95% CI -0.96 to -0.88 μm) in arteriolar diameter for those without diabetes, and a -0.58 μm difference (95% CI -0.76 to -0.41 μm) among those with diabetes. No interactions were observed for arteriolar tortuosity or venular diameters.

CONCLUSIONS/INTERPRETATION

We provide clear evidence of the modifying effect of diabetes on cardiometabolic risk factor associations with retinal microvascular architecture. These observations suggest the occurrence of preclinical disease processes, and may be a sign of impaired autoregulation due to hyperglycaemia, which has been suggested to play a pivotal role in the development of diabetes-related microvascular complications.

DATA AVAILABILITY

The data supporting the results reported here are available through the UK Biobank ( https://www.ukbiobank.ac.uk/enable-your-research/apply-for-access ).

Fractal dimension of retinal vasculature as an image quality metric for automated fundus image analysis systems

Automated fundus screening is becoming a significant programme of telemedicine in ophthalmology. Instant quality evaluation of uploaded retinal images could decrease unreliable diagnosis. In this work, we propose fractal dimension of retinal vasculature as an easy, effective and explainable indicator of retinal image quality. The pipeline of our approach is as follows: utilize image pre-processing technique to standardize input retinal images from possibly different sources to a uniform style; then, an improved deep learning empowered vessel segmentation model is employed to extract retinal vessels from the pre-processed images; finally, a box counting module is used to measure the fractal dimension of segmented vessel images. A small fractal threshold (could be a value between 1.45 and 1.50) indicates insufficient image quality. Our approach has been validated on 30,644 images from four public database.

Automated image curation in diabetic retinopathy screening using deep learning

Diabetic retinopathy (DR) screening images are heterogeneous and contain undesirable non-retinal, incorrect field and ungradable samples which require curation, a laborious task to perform manually. We developed and validated single and multi-output laterality, retinal presence, retinal field and gradability classification deep learning (DL) models for automated curation. The internal dataset comprised of 7743 images from DR screening (UK) with 1479 external test images (Portugal and Paraguay). Internal vs external multi-output laterality AUROC were right (0.994 vs 0.905), left (0.994 vs 0.911) and unidentifiable (0.996 vs 0.680). Retinal presence AUROC were (1.000 vs 1.000). Retinal field AUROC were macula (0.994 vs 0.955), nasal (0.995 vs 0.962) and other retinal field (0.997 vs 0.944). Gradability AUROC were (0.985 vs 0.918). DL effectively detects laterality, retinal presence, retinal field and gradability of DR screening images with generalisation between centres and populations. DL models could be used for automated image curation within DR screening.

Assessment of image quality on color fundus retinal images using the automatic retinal image analysis

Image quality assessment is essential for retinopathy detection on color fundus retinal image. However, most studies focused on the classification of good and poor quality without considering the different types of poor quality. This study developed an automatic retinal image analysis (ARIA) method, incorporating transfer net ResNet50 deep network with the automatic features generation approach to automatically assess image quality, and distinguish eye-abnormality-associated-poor-quality from artefact-associated-poor-quality on color fundus retinal images. A total of 2434 retinal images, including 1439 good quality and 995 poor quality (483 eye-abnormality-associated-poor-quality and 512 artefact-associated-poor-quality), were used for training, testing, and 10-ford cross-validation. We also analyzed the external validation with the clinical diagnosis of eye abnormality as the reference standard to evaluate the performance of the method. The sensitivity, specificity, and accuracy for testing good quality against poor quality were 98.0%, 99.1%, and 98.6%, and for differentiating between eye-abnormality-associated-poor-quality and artefact-associated-poor-quality were 92.2%, 93.8%, and 93.0%, respectively. In external validation, our method achieved an area under the ROC curve of 0.997 for the overall quality classification and 0.915 for the classification of two types of poor quality. The proposed approach, ARIA, showed good performance in testing, 10-fold cross validation and external validation. This study provides a novel angle for image quality screening based on the different poor quality types and corresponding dealing methods. It suggested that the ARIA can be used as a screening tool in the preliminary stage of retinopathy grading by telemedicine or artificial intelligence analysis.

State-of-the-art retinal vessel segmentation with minimalistic models

The segmentation of retinal vasculature from eye fundus images is a fundamental task in retinal image analysis. Over recent years, increasingly complex approaches based on sophisticated Convolutional Neural Network architectures have been pushing performance on well-established benchmark datasets. In this paper, we take a step back and analyze the real need of such complexity. We first compile and review the performance of 20 different techniques on some popular databases, and we demonstrate that a minimalistic version of a standard U-Net with several orders of magnitude less parameters, carefully trained and rigorously evaluated, closely approximates the performance of current best techniques. We then show that a cascaded extension (W-Net) reaches outstanding performance on several popular datasets, still using orders of magnitude less learnable weights than any previously published work. Furthermore, we provide the most comprehensive cross-dataset performance analysis to date, involving up to 10 different databases. Our analysis demonstrates that the retinal vessel segmentation is far from solved when considering test images that differ substantially from the training data, and that this task represents an ideal scenario for the exploration of domain adaptation techniques. In this context, we experiment with a simple self-labeling strategy that enables moderate enhancement of cross-dataset performance, indicating that there is still much room for improvement in this area. Finally, we test our approach on Artery/Vein and vessel segmentation from OCTA imaging problems, where we again achieve results well-aligned with the state-of-the-art, at a fraction of the model complexity available in recent literature. Code to reproduce the results in this paper is released.

Five-Year Cost-Effectiveness Modeling of Primary Care-Based, Nonmydriatic Automated Retinal Image Analysis Screening Among Low-Income Patients With Diabetes

BACKGROUND

Artificial intelligence-based technology systems offer an alternative solution for diabetic retinopathy (DR) screening compared with standard, in-office dilated eye examinations. We performed a cost-effectiveness analysis of Automated Retinal Image Analysis System (ARIAS)-based DR screening in a primary care medicine clinic that serves a low-income patient population.

METHODS

A model-based, cost-effectiveness analysis of two DR screening systems was created utilizing data from a recent study comparing adherence rates to follow-up eye care among adults ages 18 or older with a clinical diagnosis of diabetes. In the study, the patients were prescreened with an ARIAS-based, nonmydriatic (undilated), point-of-care tool in the primary care setting and were compared with patients with diabetes who were referred for dilated retinal screening without prescreening, as is the current standard of care. Using a Markov model with microsimulation resulting in a total of 600 000 simulated patient experiences, we calculated the incremental cost-utility ratio (ICUR) of the two screening approaches, with regard to five-year cost-effectiveness of DR screening and treatment of vision-threatening DR.

RESULTS

At five years, ARIAS-based screening showed similar utility as the standard of care screening systems. However, ARIAS reduced costs by 23.3%, with an ICUR of $258 721.81 comparing the current practice to ARIAS.

CONCLUSIONS

Primary care-based ARIAS DR screening is cost-effective when compared with standard of care screening methods.

Deep Learning of the Retina Enables Phenome- and Genome-Wide Analyses of the Microvasculature

BACKGROUND

The microvasculature, the smallest blood vessels in the body, has key roles in maintenance of organ health and tumorigenesis. The retinal fundus is a window for human in vivo noninvasive assessment of the microvasculature. Large-scale complementary machine learning-based assessment of the retinal vasculature with phenome-wide and genome-wide analyses may yield new insights into human health and disease.

METHODS

We used 97 895 retinal fundus images from 54 813 UK Biobank participants. Using convolutional neural networks to segment the retinal microvasculature, we calculated vascular density and fractal dimension as a measure of vascular branching complexity. We associated these indices with 1866 incident International Classification of Diseases-based conditions (median 10-year follow-up) and 88 quantitative traits, adjusting for age, sex, smoking status, and ethnicity.

RESULTS

Low retinal vascular fractal dimension and density were significantly associated with higher risks for incident mortality, hypertension, congestive heart failure, renal failure, type 2 diabetes, sleep apnea, anemia, and multiple ocular conditions, as well as corresponding quantitative traits. Genome-wide association of vascular fractal dimension and density identified 7 and 13 novel loci, respectively, that were enriched for pathways linked to angiogenesis (eg, vascular endothelial growth factor, platelet-derived growth factor receptor, angiopoietin, and WNT signaling pathways) and inflammation (eg, interleukin, cytokine signaling).

CONCLUSIONS

Our results indicate that the retinal vasculature may serve as a biomarker for future cardiometabolic and ocular disease and provide insights into genes and biological pathways influencing microvascular indices. Moreover, such a framework highlights how deep learning of images can quantify an interpretable phenotype for integration with electronic health record, biomarker, and genetic data to inform risk prediction and risk modification.

Macular Vascular Geometry Changes With Sex and Age in Healthy Subjects: A Fundus Photography Study

Purpose: To characterize the sex- and age-related alterations of the macular vascular geometry in a population of healthy eyes using fundus photography.

Methods: A cross-sectional study was conducted with 610 eyes from 305 healthy subjects (136 men, 169 women) who underwent fundus photography examination and was divided into four age groups (G1 with age ≤ 25 years, G2 with age 26–35 years, G3 with age 36–45 years, and G4 with age ≥ 46 years). A self-developed automated retinal vasculature analysis system allowed segmentation and separate multiparametric quantification of the macular vascular network according to the Early Treatment Diabetic Retinopathy Study (ETDRS). Vessel fractal dimension (D_f), vessel area rate (VAR), average vessel diameter (D_m), and vessel tortuosity (τ_n) were acquired and compared between sex and age groups.

Results: There was no significant difference between the mean age of male and female subjects (32.706 ± 10.372 and 33.494 ± 10.620, respectively, p > 0.05) and the mean age of both sexes in each age group (p > 0.05). The D_f, VAR, and D_m of the inner ring, the D_f of the outer ring, and the D_f and VAR of the whole macula were significantly greater in men than women (p < 0.001, p < 0.001, p < 0.05, respectively). There was no significant change of τ_n between males and females (p > 0.05). The D_f, VAR, and D_m of the whole macula, the inner and outer rings associated negatively with age (p < 0.001), whereas the τ_n showed no significant association with age (p > 0.05). Comparison between age groups observed that D_f started to decrease from G2 compared with G1 in the inner ring (p < 0.05) and D_f, VAR, and D_m all decreased from G3 compared with the younger groups in the whole macula, inner and outer rings (p < 0.05).

Conclusion: In the healthy subjects, macular vascular geometric parameters obtained from fundus photography showed that D_f, VAR, and D_m are related to sex and age while τ_n is not. The baseline values of the macular vascular geometry were also acquired for both sexes and all age groups.

Topological Data Analysis for Eye Fundus Image Quality Assessment

The objective of this work is to perform image quality assessment (IQA) of eye fundus images in the context of digital fundoscopy with topological data analysis (TDA) and machine learning methods. Eye health remains inaccessible for a large amount of the global population. Digital tools that automize the eye exam could be used to address this issue. IQA is a fundamental step in digital fundoscopy for clinical applications; it is one of the first steps in the preprocessing stages of computer-aided diagnosis (CAD) systems using eye fundus images. Images from the EyePACS dataset were used, and quality labels from previous works in the literature were selected. Cubical complexes were used to represent the images; the grayscale version was, then, used to calculate a persistent homology on the simplex and represented with persistence diagrams. Then, 30 vectorized topological descriptors were calculated from each image and used as input to a classification algorithm. Six different algorithms were tested for this study (SVM, decision tree, k-NN, random forest, logistic regression (LoGit), MLP). LoGit was selected and used for the classification of all images, given the low computational cost it carries. Performance results on the validation subset showed a global accuracy of 0.932, precision of 0.912 for label "quality" and 0.952 for label "no quality", recall of 0.932 for label "quality" and 0.912 for label "no quality", AUC of 0.980, F1 score of 0.932, and a Matthews correlation coefficient of 0.864. This work offers evidence for the use of topological methods for the process of quality assessment of eye fundus images, where a relatively small vector of characteristics (30 in this case) can enclose enough information for an algorithm to yield classification results useful in the clinical settings of a digital fundoscopy pipeline for CAD.

Deep learning for gradability classification of handheld, non-mydriatic retinal images

Screening effectively identifies patients at risk of sight-threatening diabetic retinopathy (STDR) when retinal images are captured through dilated pupils. Pharmacological mydriasis is not logistically feasible in non-clinical, community DR screening, where acquiring gradable retinal images using handheld devices exhibits high technical failure rates, reducing STDR detection. Deep learning (DL) based gradability predictions at acquisition could prompt device operators to recapture insufficient quality images, increasing gradable image proportions and consequently STDR detection. Non-mydriatic retinal images were captured as part of SMART India, a cross-sectional, multi-site, community-based, house-to-house DR screening study between August 2018 and December 2019 using the Zeiss Visuscout 100 handheld camera. From 18,277 patient eyes (40,126 images), 16,170 patient eyes (35,319 images) were eligible and 3261 retinal images (1490 patient eyes) were sampled then labelled by two ophthalmologists. Compact DL model area under the receiver operator characteristic curve was 0.93 (0.01) following five-fold cross-validation. Compact DL model agreement (Kappa) were 0.58, 0.69 and 0.69 for high specificity, balanced sensitivity/specificity and high sensitivity operating points compared to an inter-grader agreement of 0.59. Compact DL gradability model performance was favourable compared to ophthalmologists. Compact DL models can effectively classify non-mydriatic, handheld retinal image gradability with potential applications within community-based DR screening.

Assessing Changes in Diabetic Retinopathy Caused by Diabetes Mellitus and Glaucoma Using Support Vector Machines in Combination with Differential Evolution Algorithm

The aim of this study is to evaluate the changes related to diabetic retinopathy (DR) (no changes, small or moderate changes) in patients with glaucoma and diabetes using artificial intelligence instruments: Support Vector Machines (SVM) in combination with a powerful optimization algorithm—Differential Evolution (DE). In order to classify the DR changes and to make predictions in various situations, an approach including SVM optimized with DE was applied. The role of the optimizer was to automatically determine the SVM parameters that lead to the lowest classification error. The study was conducted on a sample of 52 patients: particularly, 101 eyes with glaucoma and diabetes mellitus, in the Ophthalmology Clinic I of the “St. Spiridon” Clinical Hospital of Iaşi. The criteria considered in the modelling action were normal or hypertensive open-angle glaucoma, intraocular hypertension and associated diabetes. The patients with other types of glaucoma pseudoexfoliation, pigment, cortisone, neovascular and primitive angle-closure, and those without associated diabetes, were excluded. The assessment of diabetic retinopathy changes were carried out with Volk lens and Fundus Camera Zeiss retinal photography on the dilated pupil, inspecting all quadrants. The criteria for classifying the DR (early treatment diabetic retinopathy study—ETDRS) changes were: without changes (absence of DR), mild forma nonproliferative diabetic retinopathy (the presence of a single micro aneurysm), moderate form (micro aneurysms, hemorrhages in 2–3 quadrants, venous dilatations and soft exudates in a quadrant), severe form (micro aneurysms, hemorrhages in all quadrants, venous dilatation in 2–3 quadrants) and proliferative diabetic retinopathy (disk and retinal neovascularization in different quadrants). Any new clinical element that occurred in subsequent checks, which led to their inclusion in severe nonproliferative or proliferative forms of diabetic retinopathy, was considered to be the result of the progression of diabetic retinopathy. The results obtained were very good; in the testing phase, a 95.23% accuracy has been obtained, only one sample being wrongly classified. The effectiveness of the classification algorithm (SVM), developed in optimal form with DE, and used in predictions of retinal changes related to diabetes, was demonstrated.

Investigation of associations between retinal microvascular parameters and albuminuria in UK Biobank: a cross-sectional case-control study

Background

Associations between microvascular variation and chronic kidney disease (CKD) have been reported previously. Non-invasive retinal fundus imaging enables evaluation of the microvascular network and may offer insight to systemic risk associated with CKD.

Methods

Retinal microvascular parameters (fractal dimension [FD] – a measure of the complexity of the vascular network, tortuosity, and retinal arteriolar and venular calibre) were quantified from macula-centred fundus images using the Vessel Assessment and Measurement Platform for Images of the REtina (VAMPIRE) version 3.1 (VAMPIRE group, Universities of Dundee and Edinburgh, Scotland) and assessed for associations with renal damage in a case-control study nested within the multi-centre UK Biobank cohort study. Participants were designated cases or controls based on urinary albumin to creatinine ratio (ACR) thresholds. Participants with ACR ≥ 3 mg/mmol (ACR stages A2-A3) were characterised as cases, and those with an ACR < 3 mg/mmol (ACR stage A1) were categorised as controls. Participants were matched on age, sex and ethnic background.

Results

Lower FD (less extensive microvascular branching) was associated with a small increase in odds of albuminuria independent of blood pressure, diabetes and other potential confounding variables (odds ratio [OR] 1.18, 95% confidence interval [CI] 1.03–1.34 for arterioles and OR 1.24, CI 1.05–1.47 for venules). Measures of tortuosity or retinal arteriolar and venular calibre were not significantly associated with ACR.

Conclusions

This study supports previously reported associations between retinal microvascular FD and other metabolic disturbances affecting the systemic vasculature. The association between retinal microvascular FD and albuminuria, independent of diabetes and blood pressure, may represent a useful indicator of systemic vascular damage associated with albuminuria.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12882-021-02273-6.

Retinal Vasculometry Associations With Glaucoma: Findings From the European Prospective Investigation of Cancer-Norfolk Eye Study

Purpose

To examine retinal vasculometry associations with different glaucomas in older British people.

Design

Cross-sectional study.

Methods

A total of 8,623 European Prospective Investigation into Cancer-Norfolk Eye study participants were examined, who underwent retinal imaging, ocular biometry assessment, and clinical ascertainment of ocular hypertensive or glaucoma status (including glaucoma suspect [GS], high-tension open-angle glaucoma [HTG], and normal-tension glaucoma [NTG]). Automated measures of arteriolar and venular tortuosity, area, and width from retinal images were obtained. MainOutcomeMeasures: Associations between glaucoma and retinal vasculometry outcomes were analyzed using multilevel linear regression, adjusted for age, sex, height, axial length, intraocular and systemic blood pressure, and within-person clustering, to provide absolute differences in width and area, and percentage differences in vessel tortuosity. Presence or absence of within-person-between-eye differences in retinal vasculometry by diagnoses were examined.

Results

A total of 565,593 vessel segments from 5,947 participants (mean age 67.6 years, SD 7.6 years, 57% women) were included; numbers with HTG, NTG, and GS in at least 1 eye were 87, 82, and 439, respectively. Thinner arterioles (−3.2 μm; 95% confidence interval [CI] −4.4 μm, −1.9 μm) and venules (−2.7 μm; 95% CI −4.9 μm, −0.5 μm) were associated with HTG. Reduced venular area was associated with HTG (−0.2 mm²; 95% CI −0.3 mm², −0.1 mm²) and NTG (−0.2 mm²; 95% CI −0.3 mm², −0.0 mm²). Less tortuous retinal arterioles and venules were associated with all glaucomas, but only significantly for GS (−3.9%; 95% CI −7.7%, −0.1% and −4.8%; 95% CI −7.4%, −2.1%, respectively). There was no evidence of within-person-between-eye differences in retinal vasculometry associations by diagnoses.

Conclusions

Retinal vessel width associations with glaucoma and novel associations with vessel area and tortuosity, together with no evidence of within-person-between-eye differences in retinal vasculometry, suggest a vascular cause of glaucoma.

•

Retinal vessel measurements, including (as a first report) vessel tortuosity and area, were associated with high-tension glaucoma and other glaucoma-related outcomes.

•

Novel analyses showing that within-person-between-eye glaucoma diagnoses, intraocular pressure, and retinal vasculometry were uncorrelated provides further evidence that systemic microvascular changes may cause glaucoma.

Retinal Vascular Tortuosity and Diameter Associations with Adiposity and Components of Body Composition

OBJECTIVE

The aim of this study was to assess whether adiposity or body composition relates to microvascular characteristics of the retina, indicative of cardiometabolic function.

METHODS

A fully automated QUARTZ software processed retinal images from 68,550 UK Biobank participants (aged 40-69 years). Differences in retinal vessel diameter and tortuosity with body composition measures from the Tanita analyzer were obtained by using multilevel regression analyses adjusted for age, sex, ethnicity, clinic, smoking, and Townsend deprivation index.

RESULTS

Venular tortuosity and diameter increased by approximately 2% (P < 10^-300 ) and 0.6 μm (P < 10^-6 ), respectively, per SD increase in BMI, waist circumference index, waist-hip ratio, total body fat mass index, and fat-free mass index (FFMI). Venular associations with adiposity persisted after adjustment for FFMI, whereas associations with FFMI were weakened by FMI adjustment. Arteriolar diameter (not tortuosity) narrowing with FFMI was independent of adiposity (-0.6 μm; -0.7 to -0.4 μm per SD increment of FFMI), while adiposity associations with arteriolar diameter were largely nonsignificant after adjustment for FFMI.

CONCLUSIONS

This demonstrates, on an unprecedented scale, that venular tortuosity and diameter are more strongly associated with adiposity, whereas arteriolar diameter relates more strongly to fat-free mass. Different attributes of the retinal microvasculature may reflect distinct roles of body composition and fatness on the cardiometabolic system.

Multiloss Function Based Deep Convolutional Neural Network for Segmentation of Retinal Vasculature into Arterioles and Venules

The arterioles and venules (AV) classification of retinal vasculature is considered as the first step in the development of an automated system for analysing the vasculature biomarker association with disease prognosis. Most of the existing AV classification methods depend on the accurate segmentation of retinal blood vessels. Moreover, the unavailability of large-scale annotated data is a major hindrance in the application of deep learning techniques for AV classification. This paper presents an encoder-decoder based fully convolutional neural network for classification of retinal vasculature into arterioles and venules, without requiring the preliminary step of vessel segmentation. An optimized multiloss function is used to learn the pixel-wise and segment-wise retinal vessel labels. The proposed method is trained and evaluated on DRIVE, AVRDB, and a newly created AV classification dataset; and it attains 96%, 98%, and 97% accuracy, respectively. The new AV classification dataset is comprised of 700 annotated retinal images, which will offer the researchers a benchmark to compare their AV classification results.

Associations of Retinal Microvascular Diameters and Tortuosity With Blood Pressure and Arterial Stiffness: United Kingdom Biobank

Supplemental Digital Content is available in the text.

To examine the baseline associations of retinal vessel morphometry with blood pressure (BP) and arterial stiffness in United Kingdom Biobank. The United Kingdom Biobank included 68 550 participants aged 40 to 69 years who underwent nonmydriatic retinal imaging, BP, and arterial stiffness index assessment. A fully automated image analysis program (QUARTZ [Quantitative Analysis of Retinal Vessel Topology and Size]) provided measures of retinal vessel diameter and tortuosity. The associations between retinal vessel morphology and cardiovascular disease risk factors/outcomes were examined using multilevel linear regression to provide absolute differences in vessel diameter and percentage differences in tortuosity (allowing within person clustering), adjusted for age, sex, ethnicity, clinic, body mass index, smoking, and deprivation index. Greater arteriolar tortuosity was associated with higher systolic BP (relative increase, 1.2%; 95% CI, 0.9; 1.4% per 10 mmHg), higher mean arterial pressure, 1.3%; 0.9, 1.7% per 10 mmHg, and higher pulse pressure (PP, 1.8%; 1.4; 2.2% per 10 mmHg). Narrower arterioles were associated with higher systolic BP (−0.9 µm; −0.94, −0.87 µm per 10 mmHg), mean arterial pressure (−1.5 µm; −1.5, −1.5 µm per 10 mmHg), PP (−0.7 µm; −0.8, −0.7 µm per 10 mmHg), and arterial stiffness index (−0.12 µm; −0.14, −0.09 µm per ms/m²). Associations were in the same direction but marginally weaker for venular tortuosity and diameter. This study assessing the retinal microvasculature at scale has shown clear associations between retinal vessel morphometry, BP, and arterial stiffness index. These observations further our understanding of the preclinical disease processes and interplay between microvascular and macrovascular disease.

A CNN-BASED RETINAL IMAGE QUALITY ASSESSMENT SYSTEM FOR TELEOPHTHALMOLOGY

Oculopathy is a widespread disease among people of all ages around the world. Teleophthalmology can facilitate the ophthalmological diagnosis for less developed countries that lack medical resources. In teleophthalmology, the assessment of retinal image quality is of great importance. In this paper, we propose a no-reference retinal image assessment system based on DenseNet, a convolutional neural network architecture. This system classified fundus images into good and bad quality or five categories: adequate, just noticeable blur, inappropriate illumination, incomplete optic disc, and opacity. The proposed system was evaluated on different datasets and compared to the applications based on other two networks: VGG-16 and GoogLenet. For binary classification, the good-and-bad binary classifier achieves an AUC of 1.000, and the degradation-specified classifiers that distinguish one specified degradation versus the rest achieve AUC values of 0.972, 0.990, 0.982, 0.982 for four categories, respectively. The multi-classification based on DenseNet achieves an overall accuracy of 0.927, which is significantly higher than 0.549 and 0.757 obtained using VGG-16 and GoogLeNet, respectively. The experimental results indicate that the proposed approach produces outstanding performance in retinal image quality assessment and is worth applying in ophthalmological telemedicine applications. In addition, the proposed approach is robust to the image noise. This study fills the gap of multi-classification in retinal image quality assessment.

Combination of Global Features for the Automatic Quality Assessment of Retinal Images

Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians and automatic methods due to poor quality. Automatic retinal image quality assessment (RIQA) is needed before image analysis. The purpose of this study was to combine novel generic quality features to develop a RIQA method. Several features were calculated from retinal images to achieve this goal. Features derived from the spatial and spectral entropy-based quality (SSEQ) and the natural images quality evaluator (NIQE) methods were extracted. They were combined with novel sharpness and luminosity measures based on the continuous wavelet transform (CWT) and the hue saturation value (HSV) color model, respectively. A subset of non-redundant features was selected using the fast correlation-based filter (FCBF) method. Subsequently, a multilayer perceptron (MLP) neural network was used to obtain the quality of images from the selected features. Classification results achieved 91.46% accuracy, 92.04% sensitivity, and 87.92% specificity. Results suggest that the proposed RIQA method could be applied in a more general computer-aided diagnosis system aimed at detecting a variety of retinal pathologies such as DR and age-related macular degeneration.

Retinal Vasculometry Associations with Cardiometabolic Risk Factors in the European Prospective Investigation of Cancer-Norfolk Study

PURPOSE

To examine associations between retinal vessel morphometry and cardiometabolic risk factors in older British men and women.

DESIGN

Retinal imaging examination as part of the European Prospective Investigation into Cancer-Norfolk Eye Study.

PARTICIPANTS

Retinal imaging and clinical assessments were carried out in 7411 participants. Retinal images were analyzed using a fully automated validated computerized system that provides novel measures of vessel morphometry.

METHODS

Associations between cardiometabolic risk factors, chronic disease, and retinal markers were analyzed using multilevel linear regression, adjusted for age, gender, and within-person clustering, to provide percentage differences in tortuosity and absolute differences in width.

MAIN OUTCOMES MEASURES

Retinal arteriolar and venular tortuosity and width.

RESULTS

In all, 279 802 arterioles and 285 791 venules from 5947 participants (mean age, 67.6 years; standard deviation [SD], 7.6 years; 57% female) were analyzed. Increased venular tortuosity was associated with higher body mass index (BMI; 2.5%; 95% confidence interval [CI], 1.7%-3.3% per 5 kg/m2), hemoglobin A1c (HbA1c) level (2.2%; 95% CI, 1.0%-3.5% per 1%), and prevalent type 2 diabetes (6.5%; 95% CI, 2.8%-10.4%); wider venules were associated with older age (2.6 μm; 95% CI, 2.2-2.9 μm per decade), higher triglyceride levels (0.6 μm; 95% CI, 0.3-0.9 μm per 1 mmol/l), BMI (0.7 μm; 95% CI, 0.4-1.0 per 5 kg/m2), HbA1c level (0.4 μm; 95% CI, -0.1 to 0.9 per 1%), and being a current smoker (3.0 μm; 95% CI, 1.7-4.3 μm); smoking also was associated with wider arterioles (2.1 μm; 95% CI, 1.3-2.9 μm). Thinner venules were associated with high-density lipoprotein (HDL) (1.4 μm; 95% CI, 0.7-2.2 per 1 mmol/l). Arteriolar tortuosity increased with age (5.4%; 95% CI, 3.8%-7.1% per decade), higher systolic blood pressure (1.2%; 95% CI, 0.5%-1.9% per 10 mmHg), in females (3.8%; 95% CI, 1.4%-6.4%), and in those with prevalent stroke (8.3%; 95% CI, -0.6% to 18%); no association was observed with prevalent myocardial infarction. Narrower arterioles were associated with age (0.8 μm; 95% CI, 0.6-1.0 μm per decade), higher systolic blood pressure (0.5 μm; 95% CI, 0.4-0.6 μm per 10 mmHg), total cholesterol level (0.2 μm; 95% CI, 0.0-0.3 μm per 1 mmol/l), and HDL (1.2 μm; 95% CI, 0.7-1.6 μm per 1 mmol/l).

CONCLUSIONS

Metabolic risk factors showed a graded association with both tortuosity and width of retinal venules, even among people without clinical diabetes, whereas atherosclerotic risk factors correlated more closely with arteriolar width, even excluding those with hypertension and cardiovascular disease. These noninvasive microvasculature measures should be evaluated further as predictors of future cardiometabolic disease.

Effective Approach to Classify and Segment Retinal Hemorrhage Using ANFIS and Particle Swarm Optimization

The main objective of this study is to progress the structure and segment the images from hemorrhage recognition in retinal fundus images in ostensible. The abnormal bleeding of blood vessels in the retina which is the membrane in the back of the eye is called retinal hemorrhage. The image folders are deliberated, and the filter technique is utilized to decrease the images specifically adaptive median filter in our suggested proposal. Gray level co-occurrence matrix (GLCM), grey level run length matrix (GLRLM) and Scale invariant feature transform (SIFT) feature skills are present after filtrating the feature withdrawal. After this, the organization technique is performed, specifically artificial neural network with fuzzy interface system (ANFIS) method; with the help of this organization, exaggerated and non-affected images are categorized. Affected hemorrhage images are transpired for segmentation procedure, and in this exertion, threshold optimization is measured with numerous optimization methods; on the basis of this, particle swarm optimization is accomplished in improved manner. Consequently, the segmented images are projected, and the sensitivity is great when associating with accurateness and specificity in the MATLAB platform.

Retinal image quality assessment using deep learning

Poor-quality retinal images do not allow an accurate medical diagnosis, and it is inconvenient for a patient to return to a medical center to repeat the fundus photography exam. In this paper, a robust automatic system is proposed to assess the quality of retinal images at the moment of the acquisition, aiming at assisting health care professionals during a fundus photography exam. We propose a convolutional neural network (CNN) pretrained on non-medical images for extracting general image features. The weights of the CNN are further adjusted via a fine-tuning procedure, resulting in a performant classifier obtained only with a small quantity of labeled images. The CNN performance was evaluated on two publicly available databases (i.e., DRIMDB and ELSA-Brasil) using two different procedures: intra-database and inter-database cross-validation. The CNN achieved an area under the curve (AUC) of 99.98% on DRIMDB and an AUC of 98.56% on ELSA-Brasil in the inter-database experiment, where training and testing were not performed on the same database. These results show the robustness of the proposed model to various image acquisitions without requiring special adaptation, thus making it a good candidate for use in operational clinical scenarios.

No-reference quality index for color retinal images

Retinal image quality assessment (RIQA) is essential to assure that the images investigated by ophthalmologists or automatic systems are suitable for reliable medical diagnosis. Measure-based RIQA techniques have several advantages over the more commonly used binary classification-based RIQA methods. Numeric quality measures can aid ophthalmologists in associating a degree of confidence to the diagnosis performed through the investigation of a certain retinal image. Moreover, a numeric quality index can provide a mean for identifying the degree of enhancement required as well as to evaluate and compare the improvement achieved by enhancement techniques. In this work, a no-reference retinal image sharpness numeric quality index is introduced that is computed from the wavelet decomposition of the images. In order to account for the obscured retinal structures in unevenly illuminated image regions, the quality index is modified by a homogeneity parameter calculated from the previously introduced retinal image saturation channel. The proposed quality index was validated and tested on two datasets having different resolutions and quality grades. A strong (Spearman's coefficient > 0.8) and statistically highly significant (p-value < 0.001) correlation was found between the introduced quality index and the subjective human scores for the two different datasets. Moreover, multiclass classification using solely the devised retinal image quality index as a feature resulted in a micro average F-measure of 0.84 and 0.95 using the high and low resolution datasets, respectively. Several comparisons with other retinal image quality measures demonstrated superiority of the proposed quality index in both performance and speed.

Automated arteriole and venule classification using deep learning for retinal images from the UK Biobank cohort

The morphometric characteristics of the retinal vasculature are associated with future risk of many systemic and vascular diseases. However, analysis of data from large population based studies is needed to help resolve uncertainties in some of these associations. This requires automated systems that extract quantitative measures of vessel morphology from large numbers of retinal images. Associations between retinal vessel morphology and disease precursors/outcomes may be similar or opposing for arterioles and venules. Therefore, the accurate detection of the vessel type is an important element in such automated systems. This paper presents a deep learning approach for the automatic classification of arterioles and venules across the entire retinal image, including vessels located at the optic disc. This comprises of a convolutional neural network whose architecture contains six learned layers: three convolutional and three fully-connected. Complex patterns are automatically learnt from the data, which avoids the use of hand crafted features. The method is developed and evaluated using 835,914 centreline pixels derived from 100 retinal images selected from the 135,867 retinal images obtained at the UK Biobank (large population-based cohort study of middle aged and older adults) baseline examination. This is a challenging dataset in respect to image quality and hence arteriole/venule classification is required to be highly robust. The method achieves a significant increase in accuracy of 8.1% when compared to the baseline method, resulting in an arteriole/venule classification accuracy of 86.97% (per pixel basis) over the entire retinal image.

Deep tessellated retinal image detection using Convolutional Neural Networks

Tessellation in fundus is not only a visible feature for aged-related and myopic maculopathy but also confuse retinal vessel segmentation. The detection of tessellated images is an inevitable processing in retinal image analysis. In this work, we propose a model using convolutional neural network for detecting tessellated images. The input to the model is pre-processed fundus image, and the output indicate whether this photograph has tessellation or not. A database with 12,000 colour retinal images is collected to evaluate the classification performance. The best tessellation classifier achieves accuracy of 97.73% and AUC value of 0.9659 using pretrained GoogLeNet and transfer learning technique.

Retinal image quality assessment based on image clarity and content

Retinal image quality assessment (RIQA) is an essential step in automated screening systems to avoid misdiagnosis caused by processing poor quality retinal images. A no-reference transform-based RIQA algorithm is introduced that assesses images based on five clarity and content quality issues: sharpness, illumination, homogeneity, field definition, and content. Transform-based RIQA algorithms have the advantage of considering retinal structures while being computationally inexpensive. Wavelet-based features are proposed to evaluate the sharpness and overall illumination of the images. A retinal saturation channel is designed and used along with wavelet-based features for homogeneity assessment. The presented sharpness and illumination features are utilized to assure adequate field definition, whereas color information is used to exclude nonretinal images. Several publicly available datasets of varying quality grades are utilized to evaluate the feature sets resulting in area under the receiver operating characteristic curve above 0.99 for each of the individual feature sets. The overall quality is assessed by a classifier that uses the collective features as an input vector. The classification results show superior performance of the algorithm in comparison to other methods from literature. Moreover, the algorithm addresses efficiently and comprehensively various quality issues and is suitable for automatic screening systems.