Retinal imaging as a source of biomarkers for diagnosis, characterization and prognosis of chronic illness or long-term conditions

Computational single fundus image restoration techniques: a review

Fundus cameras are widely used by ophthalmologists for monitoring and diagnosing retinal pathologies. Unfortunately, no optical system is perfect, and the visibility of retinal images can be greatly degraded due to the presence of problematic illumination, intraocular scattering, or blurriness caused by sudden movements. To improve image quality, different retinal image restoration/enhancement techniques have been developed, which play an important role in improving the performance of various clinical and computer-assisted applications. This paper gives a comprehensive review of these restoration/enhancement techniques, discusses their underlying mathematical models, and shows how they may be effectively applied in real-life practice to increase the visual quality of retinal images for potential clinical applications including diagnosis and retinal structure recognition. All three main topics of retinal image restoration/enhancement techniques, i.e., illumination correction, dehazing, and deblurring, are addressed. Finally, some considerations about challenges and the future scope of retinal image restoration/enhancement techniques will be discussed.

Applicability of Oculomics for Individual Risk Prediction: Repeatability and Robustness of Retinal Fractal Dimension Using DART and AutoMorph

Purpose

To investigate whether fractal dimension (FD)-based oculomics could be used for individual risk prediction by evaluating repeatability and robustness.

Methods

We used two datasets: "Caledonia," healthy adults imaged multiple times in quick succession for research (26 subjects, 39 eyes, 377 color fundus images), and GRAPE, glaucoma patients with baseline and follow-up visits (106 subjects, 196 eyes, 392 images). Mean follow-up time was 18.3 months in GRAPE; thus it provides a pessimistic lower bound because vasculature could change. FD was computed with DART and AutoMorph. Image quality was assessed with QuickQual, but no images were initially excluded. Pearson, Spearman, and intraclass correlation (ICC) were used for population-level repeatability. For individual-level repeatability, we introduce measurement noise parameter λ, which is within-eye standard deviation (SD) of FD measurements in units of between-eyes SD.

Results

In Caledonia, ICC was 0.8153 for DART and 0.5779 for AutoMorph, Pearson/Spearman correlation (first and last image) 0.7857/0.7824 for DART, and 0.3933/0.6253 for AutoMorph. In GRAPE, Pearson/Spearman correlation (first and next visit) was 0.7479/0.7474 for DART, and 0.7109/0.7208 for AutoMorph (all P < 0.0001). Median λ in Caledonia without exclusions was 3.55% for DART and 12.65% for AutoMorph and improved to up to 1.67% and 6.64% with quality-based exclusions, respectively. Quality exclusions primarily mitigated large outliers. Worst quality in an eye correlated strongly with λ (Pearson 0.5350-0.7550, depending on dataset and method, all P < 0.0001).

Conclusions

Repeatability was sufficient for individual-level predictions in heterogeneous populations. DART performed better on all metrics and might be able to detect small, longitudinal changes, highlighting the potential of robust methods.

Inflammatory mechanisms contributing to retinal alterations in HIV infection and long-term ART

People living with HIV (PLWH) may face an increased risk of eye complications associated with ageing, chronic inflammation, and the toxicity arising from long-term antiretroviral therapy (ART). This review aims to understand how inflammatory pathways contribute to retinal alterations observed in PLWH on long-term ART. This review was conducted using four electronic database searches, namely Scopus, Hinari, Google Scholar, and PubMed; from 1996 (when ART became available) until January 2022, without language restriction. Sources from clinical trials, meta-analyses, randomised controlled trials, and systematic reviews were used. Dysregulated para-inflammation (chronic inflammation) damages the blood-retina barrier, resulting in the altered retinal immune privilege and leading to the development of retinal and blood vessel changes. There is an interplay between the effects of the disease versus ART. ART causes mitochondrial toxicity, which affects the retinal ganglion cells and retinal pigment epithelium (RPE) due to oxidative stress. Infection by HIV also affects retinal microglia, which contributes to RPE damage. Both of these mechanisms affect the blood vessels. Assessing the integrity of the inner and outer blood-retina barrier is a pivotal point in pinpointing the pathogenesis of inner retinal alterations. Optical coherence tomography is a valuable tool to assess these changes. There is a paucity of research to understand how these structural changes may affect visual function, such as contrast sensitivity and colour vision.

Retina Oculomics in Neurodegenerative Disease

Ophthalmic biomarkers have long played a critical role in diagnosing and managing ocular diseases. Oculomics has emerged as a field that utilizes ocular imaging biomarkers to provide insights into systemic diseases. Advances in diagnostic and imaging technologies including electroretinography, optical coherence tomography (OCT), confocal scanning laser ophthalmoscopy, fluorescence lifetime imaging ophthalmoscopy, and OCT angiography have revolutionized the ability to understand systemic diseases and even detect them earlier than clinical manifestations for earlier intervention. With the advent of increasingly large ophthalmic imaging datasets, machine learning models can be integrated into these ocular imaging biomarkers to provide further insights and prognostic predictions of neurodegenerative disease. In this manuscript, we review the use of ophthalmic imaging to provide insights into neurodegenerative diseases including Alzheimer Disease, Parkinson Disease, Amyotrophic Lateral Sclerosis, and Huntington Disease. We discuss recent advances in ophthalmic technology including eye-tracking technology and integration of artificial intelligence techniques to further provide insights into these neurodegenerative diseases. Ultimately, oculomics opens the opportunity to detect and monitor systemic diseases at a higher acuity. Thus, earlier detection of systemic diseases may allow for timely intervention for improving the quality of life in patients with neurodegenerative disease.

Image-based insilico investigation of hemodynamics and biomechanics in healthy and diabetic human retinas

Retinal hemodynamics and biomechanics play a significant role in understanding the pathophysiology of several ocular diseases. However, these parameters are significantly affected due to changed blood vessel morphology ascribed to pathological conditions, particularly diabetes. In this study, an image-based computational fluid dynamics (CFD) model is applied to examine the effects of changed vascular morphology due to diabetes on blood flow velocity, vorticity, wall shear stress (WSS), and oxygen distribution and compare it with healthy. The 3D patient-specific vascular architecture of diabetic and healthy retina is extracted from Optical Coherence Tomography Angiography (OCTA) images and fundus to extract the capillary level information. Further, Fluid-structure interaction (FSI) simulations have been performed to compare the induced tissue stresses in diabetic and healthy conditions. Results illustrate that most arterioles possess higher velocity, vorticity, WSS, and lesser oxygen concentration than arteries for healthy and diabetic cases. However, an opposite trend is observed for venules and veins. Comparisons show that, on average, the blood flow velocity in the healthy case decreases by 42 % in arteries and 21 % in veins, respectively, compared to diabetic. In addition, the WSS and von Mises stress (VMS) in healthy case decrease by 49 % and 72 % in arteries and by 6 % and 28 % in veins, respectively, when compared with diabetic, making diabetic blood vessels more susceptible to wall rupture and tissue damage. The in-silico results may help predict the possible abnormalities region early, helping the ophthalmologists use these estimates as prognostic tools and tailor patient-specific treatment plans.

Age-related alterations in retinal capillary function

PURPOSE

To determine age-related alterations in the retinal capillary function (RCF, the ability to transport blood flow) in healthy subjects.

METHODS

A total of 148 healthy subjects (aged 18 to 83 years) were enrolled, and one eye of each subject was imaged. Retinal blood flow (RBF) was measured using a Retinal Function Imager, and retinal capillary density (RCD, expressed as fractal dimension Dbox) was measured using optical coherence tomography angiography. RCF was defined as the ratio of RBF to RCD, representing the ability to transport blood flow. The relationship between RCF and age was analyzed. In addition, the cohort was divided into four groups (G1, <35 years, G2, 35-49 years, G3, 50-64 years, and G4, ≥65 years) for further analysis.

RESULTS

With all data, the relation between the RCF and age had a trend of a quadratic model (G1-4: r = 0.16, P = 0.14). After 35 years (i.e., G2-4), the relation had a trend between the RCF and age fitted into a negative linear model (r = -0.23, P = 0.05). Moreover, after 50 years (i.e., G3-4), the negative linear model became stronger (r = -0.37, P = 0.03). The average RCF was 2.24 ± 0.22 μl/s/Dbox in G4, significantly lower than that in G2 (2.65 ± 0.56 μl/s/Dbox, P = 0.018) and G3 (2.64 ± 0.70 μl/s/Dbox, P = 0.034), but did not reach a significant level compared to that in G1 (2.55 + 0.51 μl/s/Dbox, P = 0.056).

CONCLUSIONS

This is the first study to determine age-related alterations in the RCF in a healthy population. Decreased RCF in the older group may represent a characteristic pattern of normal aging.

Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology

A leading cause of irreversible vision loss, glaucoma needs early detection for effective management. Intraocular Pressure (IOP) is a significant risk factor for glaucoma. Convolutional Neural Networks (CNN) demonstrate exceptional capabilities in analyzing retinal fundus images, a non-invasive and cost-effective imaging technique widely used in glaucoma diagnosis. By learning from large datasets of annotated images, CNN can identify subtle changes in the optic nerve head and retinal structures indicative of glaucoma. This enables early and precise glaucoma diagnosis, empowering clinicians to implement timely interventions. CNNs excel in analyzing complex medical images, detecting subtle changes indicative of glaucoma with high precision. Another valuable diagnostic tool for glaucoma evaluation, Optical Coherence Tomography (OCT), provides high-resolution cross-sectional images of the retina. CNN can effectively analyze OCT scans and extract meaningful features, facilitating the identification of structural abnormalities associated with glaucoma. Visual field testing, performed using devices like the Humphrey Field Analyzer, is crucial for assessing functional vision loss in glaucoma. The integration of CNN with retinal fundus images, OCT scans, visual field testing, and IOP measurements represents a transformative approach to glaucoma detection. These advanced technologies have the potential to revolutionize ophthalmology by enabling early detection, personalized management, and improved patient outcomes. CNNs facilitate remote expert opinions and enhance treatment monitoring. Overcoming challenges such as data scarcity and interpretability can optimize CNN utilization in glaucoma diagnosis. Measuring retinal nerve fiber layer thickness as a diagnostic marker proves valuable. CNN implementation reduces healthcare costs and improves access to quality eye care. Future research should focus on optimizing architectures and incorporating novel biomarkers. CNN integration in glaucoma detection revolutionizes ophthalmology, improving patient outcomes and access to care. This review paves the way for innovative CNN-based glaucoma detection methods. Abbreviations: CNN = Convolutional Neural Networks, AI = Artificial Intelligence, IOP = Intraocular Pressure, OCT = Optical Coherence Tomography, CLSO = Confocal Scanning Laser Ophthalmoscopy, AUC-ROC = Area Under the Receiver Operating Characteristic Curve, RNFL = Retinal Nerve Fiber Layer, RNN = Recurrent Neural Networks, VF = Visual Field, AP = Average Precision, MD = Mean Defect, sLV = square-root of Loss Variance, NN = Neural Network, WHO = World Health Organization.

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.

Retinal image enhancement based on color dominance of image

Real-time fundus images captured to detect multiple diseases are prone to different quality issues like illumination, noise, etc., resulting in less visibility of anomalies. So, enhancing the retinal fundus images is essential for a better prediction rate of eye diseases. In this paper, we propose Lab color space-based enhancement techniques for retinal image enhancement. Existing research works does not consider the relation between color spaces of the fundus image in selecting a specific channel to perform retinal image enhancement. Our unique contribution to this research work is utilizing the color dominance of an image in quantifying the distribution of information in the blue channel and performing enhancement in Lab space followed by a series of steps to optimize overall brightness and contrast. The test set of the Retinal Fundus Multi-disease Image Dataset is used to evaluate the performance of the proposed enhancement technique in identifying the presence or absence of retinal abnormality. The proposed technique achieved an accuracy of 89.53 percent.

[Retinal alterations detected by non-mydriatic retinal camera screening and referral to ophthalmology in a population with high cardiovascular risk]

OBJECTIVE

To describe the main retinal alterations detected by non-mydriatic retinal camera screening and to evaluate factors related to referral to ophthalmology in a population at high cardiovascular risk in Palmira, Colombia.

MATERIALS AND METHODS

Cross-sectional observational study, which included 11,983 photographic imaging records of patients with hypertension and diabetes mellitus from Gesencro's S.A.S. comprehensive chronic disease care program between 2018 and 2020. Risk factors associated to referral to ophthalmology were evaluated with logistic regression, and crude and adjusted ORs (odds ratios) were obtained.

RESULTS

A total of 11,880 records were analyzed; 67.7±12years old, and 69.5% were women. Among the retinal alterations were patients with diabetic retinopathy classified as more than mild in 10% and gradeI hypertensive retinopathy in 54.9% right eye, 51.9% left eye. Macular edema was also identified. Only 2069 patients (17.4%) required referral to ophthalmology, and for imaging control 82.6%. In the multivariate analysis, the risk factors associated with the probability of being referred were male gender, age 60years and older, glycosylated hemoglobin out-of-target, advanced chronic kidney disease and the microalbumin-to-creatinine ratio moderate to severely elevated.

CONCLUSION

This study makes it possible to determine the importance of screening with a non-mydriatic retinal camera in patients at high cardiovascular risk to detect retinal abnormalities and assess risk factors associated with referral to ophthalmology. Early documentation of ocular compromise in these patients could prevent and avoid visual impairment and blindness.

Application of Deep Learning to Retinal-Image-Based Oculomics for Evaluation of Systemic Health: A Review

The retina is a window to the human body. Oculomics is the study of the correlations between ophthalmic biomarkers and systemic health or disease states. Deep learning (DL) is currently the cutting-edge machine learning technique for medical image analysis, and in recent years, DL techniques have been applied to analyze retinal images in oculomics studies. In this review, we summarized oculomics studies that used DL models to analyze retinal images-most of the published studies to date involved color fundus photographs, while others focused on optical coherence tomography images. These studies showed that some systemic variables, such as age, sex and cardiovascular disease events, could be consistently robustly predicted, while other variables, such as thyroid function and blood cell count, could not be. DL-based oculomics has demonstrated fascinating, "super-human" predictive capabilities in certain contexts, but it remains to be seen how these models will be incorporated into clinical care and whether management decisions influenced by these models will lead to improved clinical outcomes.

Lower fractal dimension of retinal vessel for patients with Birdshot chorioretinopathy

PURPOSE

To identify the retinal vessel vasculature parameters associated with birdshot chorioretinopathy (BSCR).

METHODS

This retrospective observational study included 28 prevalent cases of BSCR with a median time from diagnosis of 6 years and 28 controls matched for age, arterial hypertension, diabetes and refraction. Forty-five-degree fundus images of both dilated eyes were acquired with a fundus camera (Canon CR-2, Tokyo, Japan). The summary diameter of the arterial retinal vessels (central retinal artery equivalent, CRAE), venous retinal vessels (central retinal vein equivalent, CRVE), vascular tortuosity and fractal dimension (FD) were measured using VAMPIRE software. Retinal vasculitis was characterized using fluorescein angiography and active choroiditis using indocyanine green angiography.

RESULTS

At baseline, BSCR was associated with lower FD compared with matched controls (mean difference, -0.04; 95% confidence interval [CI], -0.06 to -0.02, p < 0.001). No other VAMPIRE parameters (CRAE, CRVE, arterial and venous tortuosity) differed. Among BSCR patients, retinal vein vasculitis was associated with higher CRAE (mean difference, 21 μ; 95% CI, 2.6-40, p = 0.03), venous tortuosity (geometric mean ratio, 1.79; 95% CI, 1.18-2.72, p = 0.007) and FD (mean difference, -0.04; 95% CI, -0.06 to -0.01, p = 0.007). Resolution of retinal vein vasculitis during follow-up was paralleled by decrease in CRAE, CRVE and venous tortuosity values and increase in venous FD, respectively.

CONCLUSION

BSCR is associated with lower FD value, suggesting that chronic retinal inflammation induces microvascular remodelling. Efficient treatment of retinal vasculitis may reverse changes in retinal vascular parameters. Changes in retinal vascular parameters could be potentially useful for assessing patients with BSCR disease.

A systematic survey of advances in retinal imaging modalities for Alzheimer's disease diagnosis

Recent advances in retinal imaging pathophysiology have shown a new function for biomarkers in Alzheimer's disease diagnosis and prognosis. The significant improvements in Optical coherence tomography (OCT) retinal imaging have led to significant clinical translation, particularly in Alzheimer's disease detection. This systematic review will provide a comprehensive overview of retinal imaging in clinical applications, with a special focus on biomarker analysis for use in Alzheimer's disease detection. Articles on OCT retinal imaging in Alzheimer's disease diagnosis were identified in PubMed, Google Scholar, IEEE Xplore, and Research Gate databases until March 2021. Those studies using simultaneous retinal imaging acquisition were chosen, while those using sequential techniques were rejected. "Alzheimer's disease" and "Dementia" were searched alone and in combination with "OCT" and "retinal imaging". Approximately 1000 publications were searched, and after deleting duplicate articles, 145 relevant studies focused on the diagnosis of Alzheimer's disease utilizing retinal imaging were chosen for study. OCT has recently been demonstrated to be a valuable technique in clinical practice as according to this survey, 57% of the researchers employed optical coherence tomography, 19% used ocular fundus imaging, 13% used scanning laser ophthalmoscopy, and 11% have used multimodal imaging to diagnose Alzheimer disease. Retinal imaging has become an important diagnostic technique for Alzheimer's disease. Given the scarcity of available literature, it is clear that future prospective trials involving larger and more homogeneous groups are necessary, and the work can be expanded by evaluating its significance utilizing a machine-learning platform rather than simply using statistical methodologies.

A Detailed Systematic Review on Retinal Image Segmentation Methods

The separation of blood vessels in the retina is a major aspect in detecting ailment and is carried out by segregating the retinal blood vessels from the fundus images. Moreover, it helps to provide earlier therapy for deadly diseases and prevent further impacts due to diabetes and hypertension. Many reviews already exist for this problem, but those reviews have presented the analysis of a single framework. Hence, this article on retinal segmentation review has revealed distinct methodologies with diverse frameworks that are utilized for blood vessel separation. The novelty of this review research lies in finding the best neural network model by comparing its efficiency. For that, machine learning (ML) and deep learning (DL) were compared and have been reported as the best model. Moreover, different datasets were used to segment the retinal blood vessels. The execution of each approach is compared based on the performance metrics such as sensitivity, specificity, and accuracy using publically accessible datasets like STARE, DRIVE, ROSE, REFUGE, and CHASE. This article discloses the implementation capacity of distinct techniques implemented for each segmentation method. Finally, the finest accuracy of 98% and sensitivity of 96% were achieved for the technique of Convolution Neural Network with Ranking Support Vector Machine (CNN-rSVM). Moreover, this technique has utilized public datasets to verify efficiency. Hence, the overall review of this article has revealed a method for earlier diagnosis of diseases to deliver earlier therapy.

Self-Supervised Rigid Registration for Multimodal Retinal Images

The ability to accurately overlay one modality retinal image to another is critical in ophthalmology. Our previous framework achieved the state-of-the-art results for multimodal retinal image registration. However, it requires human-annotated labels due to the supervised approach of the previous work. In this paper, we propose a self-supervised multimodal retina registration method to alleviate the burdens of time and expense to prepare for training data, that is, aiming to automatically register multimodal retinal images without any human annotations. Specially, we focus on registering color fundus images with infrared reflectance and fluorescein angiography images, and compare registration results with several conventional and supervised and unsupervised deep learning methods. From the experimental results, the proposed self-supervised framework achieves a comparable accuracy comparing to the state-of-the-art supervised learning method in terms of registration accuracy and Dice coefficient.

Deep learning-enabled ultra-widefield retinal vessel segmentation with an automated quality-optimized angiographic phase selection tool

OBJECTIVES

To demonstrate the feasibility of a deep learning-based vascular segmentation tool for UWFA and evaluate its ability to automatically identify quality-optimized phase-specific images.

METHODS

Cumulative retinal vessel areas (RVA) were extracted from all available UWFA frames. Cubic splines were fitted for serial vascular assessment throughout the angiographic phases of eyes with diabetic retinopathy (DR), sickle cell retinopathy (SCR), or normal retinal vasculature. The image with maximum RVA was selected as the optimum early phase. A late phase frame was selected at a minimum of 4 min that most closely mirrored the RVA from the selected early image. Trained image analysts evaluated the selected pairs.

RESULTS

A total of 13,980 UWFA sequences from 462 sessions were used to evaluate the performance and 1578 UWFA sequences from 66 sessions were used to create cubic splines. Maximum RVA was detected at a mean of 41 ± 15, 47 ± 27, 38 ± 8 s for DR, SCR, and normals respectively. In 85.2% of the sessions, appropriate images for both phases were successfully identified. The individual success rate was 90.7% for early and 94.6% for late frames.

CONCLUSIONS

Retinal vascular characteristics are highly phased and field-of-view sensitive. Vascular parameters extracted by deep learning algorithms can be used for quality assessment of angiographic images and quality optimized phase selection. Clinical applications of a deep learning-based vascular segmentation and phase selection system might significantly improve the speed, consistency, and objectivity of UWFA evaluation.

Retinal vascular measures from diabetes retinal screening photographs and risk of incident dementia in type 2 diabetes: A GoDARTS study

Objective

Patients with diabetes have an increased risk of dementia. Improved prediction of dementia is an important goal in developing future prevention strategies. Diabetic retinopathy screening (DRS) photographs may be a convenient source of imaging biomarkers of brain health. We therefore investigated the association of retinal vascular measures (RVMs) from DRS photographs in patients with type 2 diabetes with dementia risk.

Research Design and Methods

RVMs were obtained from 6,111 patients in the GoDARTS bioresource (635 incident cases) using VAMPIRE software. Their association, independent of Apo E4 genotype and clinical parameters, was determined for incident all cause dementia (ACD) and separately Alzheimer's disease (AD) and vascular dementia (VD). We used Cox’s proportional hazards with competing risk of death without dementia. The potential value of RVMs to increase the accuracy of risk prediction was evaluated.

Results

Increased retinal arteriolar fractal dimension associated with increased risk of ACD (csHR 1.17; 1.08–1.26) and AD (HR 1.33; 1.16–1.52), whereas increased venular fractal dimension (FDV) was associated with reduced risk of AD (csHR 0.85; 0.74–0.96). Conversely, FDV was associated with increased risk of VD (csHR 1.22; 1.07–1.40). Wider arteriolar calibre was associated with a reduced risk of ACD (csHR 0.9; 0.83–0.98) and wider venular calibre was associated with a reduced risk of AD (csHR 0.87; 0.78–0.97). Accounting for competing risk did not substantially alter these findings. RVMs significantly increased the accuracy of prediction.

Conclusions

Conventional DRS photographs could enhance stratifying patients with diabetes at increased risk of dementia facilitating the development of future prevention strategies.

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy.

Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning

Purpose: We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI). Methods: Participants who had undergone brain MRI and health-screening fundus photography at Hallym University Sacred Heart Hospital between 2010 and 2020 were consecutively included. The subjects were divided based on the presence of WMH, then classified into three groups according to the FS grade (0 vs. 1 vs. 2+) using age matching. Two pre-trained convolutional neural networks were fine-tuned and evaluated for prediction performance using 10-fold cross-validation. Results: A total of 3726 fundus photographs from 1892 subjects were included, of which 905 fundus photographs from 462 subjects were included in the age-matched balanced dataset. In predicting the presence of WMH, the mean area under the receiver operating characteristic curve was 0.736 ± 0.030 for DenseNet-201 and 0.724 ± 0.026 for EfficientNet-B7. For the prediction of FS grade, the mean accuracies reached 41.4 ± 5.7% with DenseNet-201 and 39.6 ± 5.6% with EfficientNet-B7. The deep learning models focused on the macula and retinal vasculature to detect an FS of 2+. Conclusions: Cerebral WMH might be partially predicted by non-invasive fundus photography via deep learning, which may suggest an eye–brain association.

Arterial Hypertension and the Hidden Disease of the Eye: Diagnostic Tools and Therapeutic Strategies

Hypertension is a major cardiovascular risk factor that is responsible for a heavy burden of morbidity and mortality worldwide. A critical aspect of cardiovascular risk estimation in hypertensive patients depends on the assessment of hypertension-mediated organ damage (HMOD), namely the generalized structural and functional changes in major organs induced by persistently elevated blood pressure values. The vasculature of the eye shares several common structural, functional, and embryological features with that of the heart, brain, and kidney. Since retinal microcirculation offers the unique advantage of being directly accessible to non-invasive and relatively simple investigation tools, there has been considerable interest in the development and modernization of techniques that allow the assessment of the retinal vessels’ structural and functional features in health and disease. With the advent of artificial intelligence and the application of sophisticated physics technologies to human sciences, consistent steps forward have been made in the study of the ocular fundus as a privileged site for diagnostic and prognostic assessment of diverse disease conditions. In this narrative review, we will recapitulate the main ocular imaging techniques that are currently relevant from a clinical and/or research standpoint, with reference to their pathophysiological basis and their possible diagnostic and prognostic relevance. A possible non pharmacological approach to prevent the onset and progression of retinopathy in the presence of hypertension and related cardiovascular risk factors and diseases will also be discussed.

Concordance between SIVA, IVAN, and VAMPIRE Software Tools for Semi-Automated Analysis of Retinal Vessel Caliber

We aimed to compare measurements from three of the most widely used software packages in the literature and to generate conversion algorithms for measurement of the central retinal artery equivalent (CRAE) and central retinal vein equivalent (CRVE) between SIVA and IVAN and between SIVA and VAMPIRE. We analyzed 223 retinal photographs from 133 human participants using both SIVA, VAMPIRE and IVAN independently for computing CRAE and CRVE. Agreement between measurements was assessed using Bland–Altman plots and intra-class correlation coefficients. A conversion algorithm between measurements was carried out using linear regression, and validated using bootstrapping and root-mean-square error. The agreement between VAMPIRE and IVAN was poor to moderate: The mean difference was 20.2 µm (95% limits of agreement, LOA, −12.2–52.6 µm) for CRAE and 21.0 µm (95% LOA, −17.5–59.5 µm) for CRVE. The agreement between VAMPIRE and SIVA was also poor to moderate: the mean difference was 36.6 µm (95% LOA, −12.8–60.4 µm) for CRAE, and 40.3 µm (95% LOA, 5.6–75.0 µm) for CRVE. The agreement between IVAN and SIVA was good to excellent: the mean difference was 16.4 µm (95% LOA, −4.25–37.0 µm) for CRAE, and 19.3 µm (95% LOA, 0.09–38.6 µm) for CRVE. We propose an algorithm converting IVAN and VAMPIRE measurements into SIVA-estimated measurements, which could be used to homogenize sets of vessel measurements obtained with different software packages.

Cardiovascular Risk Stratification in Diabetic Retinopathy via Atherosclerotic Pathway in COVID-19/non-COVID-19 Frameworks using Artificial Intelligence Paradigm: A Narrative Review

Diabetes is one of the main causes of the rising cases of blindness in adults. This microvascular complication of diabetes is termed diabetic retinopathy (DR) and is associated with an expanding risk of cardiovascular events in diabetes patients. DR, in its various forms, is seen to be a powerful indicator of atherosclerosis. Further, the macrovascular complication of diabetes leads to coronary artery disease (CAD). Thus, the timely identification of cardiovascular disease (CVD) complications in DR patients is of utmost importance. Since CAD risk assessment is expensive for low-income countries, it is important to look for surrogate biomarkers for risk stratification of CVD in DR patients. Due to the common genetic makeup between the coronary and carotid arteries, low-cost, high-resolution imaging such as carotid B-mode ultrasound (US) can be used for arterial tissue characterization and risk stratification in DR patients. The advent of artificial intelligence (AI) techniques has facilitated the handling of large cohorts in a big data framework to identify atherosclerotic plaque features in arterial ultrasound. This enables timely CVD risk assessment and risk stratification of patients with DR. Thus, this review focuses on understanding the pathophysiology of DR, retinal and CAD imaging, the role of surrogate markers for CVD, and finally, the CVD risk stratification of DR patients. The review shows a step-by-step cyclic activity of how diabetes and atherosclerotic disease cause DR, leading to the worsening of CVD. We propose a solution to how AI can help in the identification of CVD risk. Lastly, we analyze the role of DR/CVD in the COVID-19 framework.

Association of cigarette smoking with retinal capillary plexus: an optical coherence tomography angiography study

PURPOSE

To investigate the association between cigarette smoking and retinal capillary plexus (RCP) using optical coherence tomography angiography (OCTA) and to examine whether potential vascular risk factors could impact their association.

METHODS

This is a cross-sectional, community-based study. The Jidong Eye Cohort Study included participants aged ≥18 years in the Jidong community (Tangshan city, northern China) from August 2019 to January 2020. All participants underwent comprehensive ophthalmic examination and completed detailed smoking questionnaires. Retinal vessel density in the superficial and deep RCP was automatically measured using OCTA.

RESULTS

Of the 2598 participants included in the study, 2026 (78.0%) never smoked and 572 (22.0%) had a history of smoking (494 [19.0%] current smokers and 78 [3.0%] former smokers). The median (interquartile range) age was 41 (34-52) years for the non-smoking group and 45 (35-54.5) years for the smoking group. Multivariable analysis showed that smoking history is associated with a low deep RCP vessel density in the parafovea (β, -0.53; 95% confidence interval [CI], -0.82 to -0.24) and four quadrants. Increased smoking pack-years were associated with reduced deep RCP vessel density in the parafovea (p for trend <0.001) and four quadrants. The significant interaction between diabetes and smoking only was found for superficial RCP vessel density in the parafovea (p for interaction = 0.014) and four quadrants except for the temporal quadrants.

CONCLUSIONS

Cigarette smoking is an independent risk factor for reduced deep RCP vessel density. Our findings imply the potential detrimental effect of smoking on the occurrence of ocular diseases.

Improving sensitivity and connectivity of retinal vessel segmentation via error discrimination network

PURPOSE

Automated retinal vessel segmentation is crucial to the early diagnosis and treatment of ophthalmological diseases. Many deep learning-based methods have shown exceptional success in this task. However, current approaches are still inadequate in challenging vessels (e.g., thin vessels) and rarely focus on the connectivity of vessel segmentation.

METHODS

We propose using an error discrimination network (D) to distinguish whether the vessel pixel predictions of the segmentation network (S) are correct, and S is trained to obtain fewer error predictions of D. Our method is similar to, but not the same as, the generative adversarial network (GAN). Three types of vessel samples and corresponding error masks are used to train D, as follows: (1) vessel ground truth; (2) vessel segmented by S; (3) artificial thin vessel error samples that further improve the sensitivity of D to wrong small vessels. As an auxiliary loss function of S, D strengthens the supervision of difficult vessels. Optionally, we can use the errors predicted by D to correct the segmentation result of S.

RESULTS

Compared with state-of-the-art methods, our method achieves the highest scores in sensitivity (86.19%, 86.26%, and 86.53%) and G-Mean (91.94%, 91.30%, and 92.76%) on three public datasets, namely, STARE, DRIVE, and HRF. Our method also maintains a competitive level in other metrics. On the STARE dataset, the F1-score and AUC of our method rank second and first, respectively, reaching 84.51% and 98.97%. The top scores of the three topology-relevant metrics (Conn, Inf, and Cor) demonstrate that the vessels extracted by our method have excellent connectivity. We also validate the effectiveness of error discrimination supervision and artificial error sample training through ablation experiments.

CONCLUSIONS

The proposed method provides an accurate and robust solution for difficult vessel segmentation. This article is protected by copyright. All rights reserved.

Association of Neuroretinal Thinning and Microvascular Changes with Hypertension in an Older Population in Southern Italy

Background: Retinal microvasculature assessment at capillary level may potentially aid the evaluation of early microvascular changes due to hypertension. We aimed to investigate associations between the measures obtained using optical coherence tomography (OCT) and OCT-angiography (OCT-A) and hypertension, in a southern Italian older population. Methods: We performed a cross-sectional analysis from a population-based study on 731 participants aged 65 years+ subdivided into two groups according to the presence or absence of blood hypertension without hypertensive retinopathy. The average thickness of the ganglion cell complex (GCC) and the retinal nerve fiber layer (RNFL) were measured. The foveal avascular zone area, vascular density (VD) at the macular site and of the optic nerve head (ONH) and radial peripapillary capillary (RPC) plexi were evaluated. Logistic regression was applied to assess the association of ocular measurements with hypertension. Results: GCC thickness was inversely associated with hypertension (odds ratio (OR): 0.98, 95% confidence interval (CI): 0.97–1). A rarefaction of VD of the ONH plexus at the inferior temporal sector (OR: 0.95, 95% CI: 0.91–0.99) and, conversely, a higher VD of the ONH and RPC plexi inside optic disc (OR: 1.07, 95% CI: 1.04–1.10; OR: 1.04, 95% CI: 1.02–1.06, respectively) were significantly associated with hypertension. Conclusion: A neuroretinal thinning involving GCC and a change in capillary density at the peripapillary network were related to the hypertension in older patients without hypertensive retinopathy. Assessing peripapillary retinal microvasculature using OCT-A may be a useful non-invasive approach to detect early microvascular changes due to hypertension.

Measuring axial length of the eye from magnetic resonance brain imaging

BACKGROUND

Metrics derived from the human eye are increasingly used as biomarkers and endpoints in studies of cardiovascular, cerebrovascular and neurological disease. In this context, it is important to account for potential confounding that can arise from differences in ocular dimensions between individuals, for example, differences in globe size.

METHODS

We measured axial length, a geometric parameter describing eye size from T2-weighted brain MRI scans using three different image analysis software packages (Mango, ITK and Carestream) and compared results to biometry measurements from a specialized ophthalmic instrument (IOLMaster 500) as the reference standard.

RESULTS

Ninety-three healthy research participants of mean age 51.0 ± SD 5.4 years were analyzed. The level of agreement between the MRI-derived measurements and the reference standard was described by mean differences as follows, Mango - 0.8 mm; ITK - 0.5 mm; and Carestream - 0.1 mm (upper/lower 95% limits of agreement across the three tools ranged from 0.9 mm to - 2.6 mm). Inter-rater reproducibility was between - 0.03 mm and 0.45 mm (ICC 0.65 to 0.93). Intra-rater repeatability was between 0.0 mm and - 0.2 mm (ICC 0.90 to 0.95).

CONCLUSIONS

We demonstrate that axial measurements of the eye derived from brain MRI are within 3.5% of the reference standard globe length of 24.1 mm. However, the limits of agreement could be considered clinically significant. Axial length of the eye obtained from MRI is not a replacement for the precision of biometry, but in the absence of biometry it could provide sufficient accuracy to act as a proxy. We recommend measuring eye axial length from MRI in studies that do not have biometry but use retinal imaging to study neurodegenerative changes so as to control for differing eye size across individuals.

Development of a Novel Retina-Based Diagnostic Score for Early Detection of Major Depressive Disorder: An Interdisciplinary View

BACKGROUND

Clinically effective markers for the diagnosis of major depressive disorder (MDD) are lacking. Alterations in retinal features are closely related to the pathophysiological progression of MDD. However, the reliable retina-related diagnostic model for MDD remains to be developed. Thus, our study aimed to quantitatively evaluate retinal vascular and structural changes in MDD patients and to develop a reliable diagnostic model of MDD based on retinal parameters.

METHODS

Seventy-eight patients with MDD and 47 healthy controls (HCs) underwent retinal vessel density and structure examination using optical coherence tomography angiography and visual field examination using perimetry. Independent-sample t test was used to assess the differences in retinal parameters between the groups. Meanwhile, we constructed the corresponding retina-based diagnostic model by LASSO logistic regression. Finally, the diagnostic ability of the model was evaluated by area under the curve (AUC) of receiver operating characteristic curves and calibration plot of nomogram.

RESULTS

MDD patients showed lower retinal vessel density (including radial peripapillary capillary vessel density, superficial and deep capillary plexus vessel density), thinner subfoveal choroidal thickness, and poorer visual fields compared to HCs (all p < 0.05). Furthermore, a retina-based diagnostic model was constructed and shows a strong diagnostic capability for MDD (AUC = 0.9015, p < 0.001).

CONCLUSION

Patients with MDD showed distinct retinal features compared to HCs. The retina-based diagnostic model is expected to be a necessary complement to the diagnosis of MDD.

Association of Serum Uric Acid With Retinal Capillary Plexus

BACKGROUND

To determine the association between serum uric acid (SUA) and the retinal capillary plexus (RCP) using optical coherence tomography angiography (OCTA).

METHODS

This cross-sectional study evaluated data from August 2019 to January 2020 from participants recruited from the Jidong community (Tangshan, Hebei, China). All participants completed detailed anthropometrical measurements, laboratory tests and comprehensive ophthalmic examinations. We assessed the vessel density in RCP using OCTA. We used multivariable analysis to evaluate the sex-specific association between SUA and RCP after adjusting for confounders.

RESULTS

A total of 2730 participants were included in this study. The mean age of the participants was 44.0 ± 11.6 years, and 1463 (53.6%) were women. The multivariable βs and 95% confidence intervals (CIs) of superficial RCP vessel density in the second through fourth SUA quartiles compared with the lowest SUA quartiles were -0.27 (-0.56 - 0.03), -0.30 (-0.60 - 0.01), and -0.46 (-0.78 - -0.14) (P for trend = 0.007) in men.

CONCLUSIONS

Higher SUA levels were significantly associated with lower RCP vessel density in men. Our findings provide evidence for the detrimental effect of high SUA levels on the retinal microvasculature and imply the importance of modulating SUA to prevent the microvascular alternation especially for men.

Estimation of stroke severity with National Institutes of Health Stroke Scale grading and retinal features: A cross-sectional study

To estimate National Institutes of Health Stroke Scale (NIHSS) grading of stroke patients with retinal characteristics.A cross-sectional study was conducted in Shenzhen Traditional Chinese Medicine Hospital. Baseline information and retinal photos were collected within 2 weeks of admission. An NIHSS score was measured for each patient by trained doctors. Patients were classified into 0 to 4 score group and 5 to 42 score group for analysis. Three multivariate logistic models, with traditional clinical characteristics alone, with retinal characteristics alone, and with both, were built.For clinical characteristics, hypertension duration is statistically significantly associated with higher NIHSS score (P = .014). Elevated total homocysteine levels had an OR of 0.456 (P = .029). For retinal characteristics, the fractal dimension of the arteriolar network had an OR of 0.245 (P < .001) for the left eyes, and an OR of 0.417 (P = .009) for right eyes. The bifurcation coefficient of the arteriole of the left eyes had an OR of 2.931 (95% CI 1.573-5.46, P = .001), the nipping of the right eyes had an OR of 0.092 (P = .003) showed statistical significance in the model.The area under receiver-operating characteristic curve increased from 0.673, based on the model with clinical characteristics alone, to 0.896 for the model with retinal characteristics alone and increased to 0.931 for the model with both clinical and retinal characteristics combined.Retinal characteristics provided more information than clinical characteristics in estimating NIHSS grading and can provide us with an objective method for stroke severity estimation.

BSEResU-Net: An attention-based before-activation residual U-Net for retinal vessel segmentation

BACKGROUND AND OBJECTIVES

Retinal vessels are a major feature used for the physician to diagnose many retinal diseases, such as cardiovascular disease and Glaucoma. Therefore, the designing of an auto-segmentation algorithm for retinal vessel draw great attention in medical field. Recently, deep learning methods, especially convolutional neural networks (CNNs) show extraordinary potential for the task of vessel segmentation. However, most of the deep learning methods only take advantage of the shallow networks with a traditional cross-entropy objective, which becomes the main obstacle to further improve the performance on a task that is imbalanced. We therefore propose a new type of residual U-Net called Before-activation Squeeze-and-Excitation ResU-Net (BSEResu-Net) to tackle the aforementioned issues.

METHODS

Our BSEResU-Net can be viewed as an encoder/decoder framework that constructed by Before-activation Squeeze-and-Excitation blocks (BSE Blocks). In comparison to the current existing CNN structures, we utilize a new type of residual block structure, namely BSE block, in which the attention mechanism is combined with skip connection to boost the performance. What's more, the network could consistently gain accuracy from the increasing depth as we incorporate more residual blocks, attributing to the dropblock mechanism used in BSE blocks. A joint loss function which is based on the dice and cross-entropy loss functions is also introduced to achieve more balanced segmentation between the vessel and non-vessel pixels.

RESULTS

The proposed BSEResU-Net is evaluated on the publicly available DRIVE, STARE and HRF datasets. It achieves the F1-score of 0.8324, 0.8368 and 0.8237 on DRIVE, STARE and HRF dataset, respectively. Experimental results show that the proposed BSEResU-Net outperforms current state-of-the-art algorithms.

CONCLUSIONS

The proposed algorithm utilizes a new type of residual blocks called BSE residual blocks for vessel segmentation. Together with a joint loss function, it shows outstanding performance both on low and high-resolution fundus images.

Predicting sex from retinal fundus photographs using automated deep learning

Deep learning may transform health care, but model development has largely been dependent on availability of advanced technical expertise. Herein we present the development of a deep learning model by clinicians without coding, which predicts reported sex from retinal fundus photographs. A model was trained on 84,743 retinal fundus photos from the UK Biobank dataset. External validation was performed on 252 fundus photos from a tertiary ophthalmic referral center. For internal validation, the area under the receiver operating characteristic curve (AUROC) of the code free deep learning (CFDL) model was 0.93. Sensitivity, specificity, positive predictive value (PPV) and accuracy (ACC) were 88.8%, 83.6%, 87.3% and 86.5%, and for external validation were 83.9%, 72.2%, 78.2% and 78.6% respectively. Clinicians are currently unaware of distinct retinal feature variations between males and females, highlighting the importance of model explainability for this task. The model performed significantly worse when foveal pathology was present in the external validation dataset, ACC: 69.4%, compared to 85.4% in healthy eyes, suggesting the fovea is a salient region for model performance OR (95% CI): 0.36 (0.19, 0.70) p = 0.0022. Automated machine learning (AutoML) may enable clinician-driven automated discovery of novel insights and disease biomarkers.

Retinal venular tortuosity and fractal dimension predict incident retinopathy in adults with type 2 diabetes: the Edinburgh Type 2 Diabetes Study

AIMS/HYPOTHESIS

Our aim was to determine whether a range of prespecified retinal vessel traits were associated with incident diabetic retinopathy in adults with type 2 diabetes.

METHODS

In the prospective observational cohort Edinburgh Type 2 Diabetes Study of 1066 adults with type 2 diabetes, aged 60-75 years at recruitment, 718 were free from diabetic retinopathy at baseline. Baseline retinal traits including vessel widths, tortuosity (curvature) and fractal dimensions (network complexity), were quantified using fundus camera images and semiautomated software, and analysed using logistic regression for their association with incident diabetic retinopathy over 10 years.

RESULTS

The incidence of diabetic retinopathy was 11.4% (n = 82) over 10 years. After adjustment for a range of vascular and diabetes-related risk factors, both increased venular tortuosity (OR 1.51; 95% CI 1.15, 1.98; p = 0.003) and decreased fractal dimension (OR 0.75; 95% CI 0.58, 0.96; p = 0.025) were associated with incident retinopathy. There was no evidence of an association with arterial tortuosity, and associations between measurements of vessel widths and retinopathy lost statistical significance after adjustment for diabetes-related factors and vascular disease. Adding venular tortuosity to a model including established risk factors for diabetic retinopathy (HbA_1c, BP and kidney function) improved the discriminative ability (C statistic increased from 0.624 to 0.640, p = 0.013), but no such benefit was found with fractal dimension.

CONCLUSIONS/INTERPRETATION

Increased retinal venular tortuosity and decreased fractal dimension are associated with incident diabetic retinopathy, independent of classical risk factors. There is some evidence that venular tortuosity may be a useful biomarker to improve the predictive ability of models based on established retinopathy risk factors, and its inclusion in further risk prediction modelling is warranted.

On the quantitative effects of compression of retinal fundus images on morphometric vascular measurements in VAMPIRE

BACKGROUND AND OBJECTIVES

This paper reports a quantitative analysis of the effects of joint photographic experts group (JPEG) image compression of retinal fundus camera images on automatic vessel segmentation and on morphometric vascular measurements derived from it, including vessel width, tortuosity and fractal dimension.

METHODS

Measurements are computed with vascular assessment and measurement platform for images of the retina (VAMPIRE), a specialized software application adopted in many international studies on retinal biomarkers. For reproducibility, we use three public archives of fundus images (digital retinal images for vessel extraction (DRIVE), automated retinal image analyzer (ARIA), high-resolution fundus (HRF)). We generate compressed versions of original images in a range of representative levels.

RESULTS

We compare the resulting vessel segmentations with ground truth maps and morphological measurements of the vascular network with those obtained from the original (uncompressed) images. We assess the segmentation quality with sensitivity, specificity, accuracy, area under the curve and Dice coefficient. We assess the agreement between VAMPIRE measurements from compressed and uncompressed images with correlation, intra-class correlation and Bland-Altman analysis.

CONCLUSIONS

Results suggest that VAMPIRE width-related measurements (central retinal artery equivalent (CRAE), central retinal vein equivalent (CRVE), arteriolar-venular width ratio (AVR)), the fractal dimension (FD) and arteriolar tortuosity have excellent agreement with those from the original images, remaining substantially stable even for strong loss of quality (20% of the original), suggesting the suitability of VAMPIRE in association studies with compressed images.

Robust Content-Adaptive Global Registration for Multimodal Retinal Images Using Weakly Supervised Deep-Learning Framework

Multimodal retinal imaging plays an important role in ophthalmology. We propose a content-adaptive multimodal retinal image registration method in this paper that focuses on the globally coarse alignment and includes three weakly supervised neural networks for vessel segmentation, feature detection and description, and outlier rejection. We apply the proposed framework to register color fundus images with infrared reflectance and fluorescein angiography images, and compare it with several conventional and deep learning methods. Our proposed framework demonstrates a significant improvement in robustness and accuracy reflected by a higher success rate and Dice coefficient compared with other methods.

Retinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research

The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. Early detection and diagnosis of ocular pathologies would enable forestall of visual impairment. One challenge that limits the adoption of computer-aided diagnosis tool by ophthalmologists is the number of sight-threatening rare pathologies, such as central retinal artery occlusion or anterior ischemic optic neuropathy, and others are usually ignored. In the past two decades, many publicly available datasets of color fundus images have been collected with a primary focus on diabetic retinopathy, glaucoma, age-related macular degeneration and few other frequent pathologies. To enable development of methods for automatic ocular disease classification of frequent diseases along with the rare pathologies, we have created a new Retinal Fundus Multi-disease Image Dataset (RFMiD). It consists of 3200 fundus images captured using three different fundus cameras with 46 conditions annotated through adjudicated consensus of two senior retinal experts. To the best of our knowledge, our dataset, RFMiD, is the only publicly available dataset that constitutes such a wide variety of diseases that appear in routine clinical settings. This dataset will enable the development of generalizable models for retinal screening.

Association of reduced retinal arteriolar tortuosity with depression in older participants from the Northern Ireland Cohort for the Longitudinal Study of Ageing

INTRODUCTION

The retina shares similar anatomical and physiological features with the brain and subtle variations in retinal microvascular parameters (RMPs) may reflect similar vascular variation in the brain. The aim of this study was to assess associations between RMPs and measures of depression in the Northern Ireland Cohort for the Longitudinal Study of Ageing.

METHODS

RMPs (arteriolar and venular caliber, fractal dimension and tortuosity) were measured from optic disc centred fundus images using semi-automated software. Depression was characterised by the Centre for Epidemiologic Studies Depression Scale (CES-D) in the absence of mild cognitive impairment or use of anti-depressive medications. Associations between depression and RMPs were assessed by regression analyses with adjustment for potential confounders.

RESULTS

Data were available for 1376 participants of which 113 (8.2%) and 1263 (91.8%) were classified with and without depression. Participants had a mean age of 62.0 ± 8.4 yrs., 52% were female, and 8% were smokers. Individuals with depression had a higher CES-D score than those without (22.0 ± 6.2 versus 4.4 ± 3.9). Lower values of arteriolar tortuosity were significantly associated with depression, before and after adjustment for potential confounders (odds ratio = 0.79; 95% confidence intervals: 0.65, 0.96; P = 0.02).

CONCLUSION

Decreased retinal arteriolar tortuosity, a measure of the complexity of the retinal microvasculature was associated with depression in older adults independent of potential confounding factors. Retinal measures may offer opportunistic assessment of microvascular health associated with outcomes of depression.

Retinal vascular caliber changes after laser photocoagulation in diabetic retinopathy

BACKGROUND Diabetic retinopathy causes vascular dilatation caused by hypoxia, whereas oxygen tension improvement leads to retinal vessels narrowing. Given that laser photocoagulation aims to increase the oxygen tension in the retina, we hypothesized that the narrowing of vessel caliber after the treatment could be possibly demonstrated. This study aimed to assess the changes in the caliber of retinal vessels before and after laser photocoagulation in diabetic retinopathy. METHODS This research was a prospective cohort study on the treatment of diabetic retinopathy by laser photocoagulation, and it was conducted at Universitas Hasanuddin Hospital, Makassar, Indonesia between November 2017–April 2018. Retinal vascular caliber changes were analyzed before and 6–8 weeks after photocoagulation in 30 diabetic eyes. Central retinal arteriolar equivalent (CRAE) and central retinal venular equivalent (CRVE) were measured using the vessel assessment and measurement platform software for images of the retina (VAMPIRE) manual annotation tool. RESULTS A significant decrease of CRVE was observed after laser photocoagulation (p<0.001), but CRAE was not reduced significantly (p = 0.067). No difference was recorded between CRVE and CRAE post-laser photocoagulation (p = 0.14), implying a reduction in vein caliber toward normal in the treated eyes. CONCLUSIONS Laser photocoagulation decreases the CRVE in diabetic retinopathy despite the absence of changes in the grade of diabetic retinopathy.

A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification

The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images.

Longitudinal assessment of quantitative ultra-widefield ischaemic and vascular parameters in sickle cell retinopathy

PURPOSE

To evaluate longitudinal quantitative ischaemic and vasculature parameters, including ischaemic index, vessel area, length and geodesic distance in sickle cell retinopathy (SCR) on ultra-widefield fluorescein angiography (UWFA).

METHODS

Optimal UWFA images from two longitudinal timepoints of 74 eyes from 45 patients with SCR were aligned and a common region of interest was determined. A deep-learning augmented ischaemia and vascular segmentation platform was used for feature extraction. Geodesic distance maps demonstrating the shortest distance within the vascular masks from the centre of the optic disc were created. Ischaemic index, vessel area, vessel length and geodesic distance were measured. Paired t-test and linear mixed effect model analysis were performed.

RESULTS

Overall, 25 (44 eyes) patients with HbSS, 14 (19 eyes) with HbSC, 6 (11 eyes) with HbSthal and other genotypes were included. Mean age was 40.1±11.0 years. Mean time interval between two UWFA studies was 23.0±15.1 months (range: 3-71.3). Mean panretinal ischaemic index increased from 10.0±7.2% to 10.9±7.3% (p<0.005). Mean rate of change in ischaemic index was 0.5±0.7% per year. Mean vessel area (p=0.020) and geodesic distance (p=0.048) decreased significantly. Multivariate analysis demonstrated baseline ischaemic index and Goldberg stage are correlated with progression.

CONCLUSION

Longitudinal ischaemic index and retinal vascular parameter measurements demonstrate statistically significant progression in SCR. The clinical significance of these relatively small magnitude changes remains unclear but may provide insights into the progression of retinal ischaemia in SCR.

Rationale and design of a longitudinal study of cerebral small vessel diseases, clinical and imaging outcomes in patients presenting with mild ischaemic stroke: Mild Stroke Study 3

Background

Cerebral small vessel disease is a major cause of dementia and stroke, visible on brain magnetic resonance imaging. Recent data suggest that small vessel disease lesions may be dynamic, damage extends into normal-appearing brain and microvascular dysfunctions include abnormal blood–brain barrier leakage, vasoreactivity and pulsatility, but much remains unknown regarding underlying pathophysiology, symptoms, clinical features and risk factors of small vessel disease.

Patients and Methods: The Mild Stroke Study 3 is a prospective observational cohort study to identify risk factors for and clinical implications of small vessel disease progression and regression among up to 300 adults with non-disabling stroke. We perform detailed serial clinical, cognitive, lifestyle, physiological, retinal and brain magnetic resonance imaging assessments over one year; we assess cerebrovascular reactivity, blood flow, pulsatility and blood–brain barrier leakage on magnetic resonance imaging at baseline; we follow up to four years by post and phone. The study is registered ISRCTN 12113543.

Summary

Factors which influence direction and rate of change of small vessel disease lesions are poorly understood. We investigate the role of small vessel dysfunction using advanced serial neuroimaging in a deeply phenotyped cohort to increase understanding of the natural history of small vessel disease, identify those at highest risk of early disease progression or regression and uncover novel targets for small vessel disease prevention and therapy.

Vascular bifurcation mapping with photoacoustic microscopy

The early detection of microvascular changes in cancer diagnosis is needed in the clinic. A change in the vascular bifurcation density is a biomarker for the sprouting activity. Here, Optical-Resolution PhotoAcoustic Microscopy is used for quantitative vascular bifurcation mapping in 2D after the creation of Virtual Tubes out of Bifurcations. In stacks of OR-PAM images of the hemoglobin distribution, bifurcations become tubes and are selected by the 3D tubeness filter. These fast analyses will be compared to a classical approach and are easier to implement for functional analysis of the vascular bifurcation density in healthy and diseased tissues.

Evaluation of macular thickness and volume tested by optical coherence tomography as biomarkers for Alzheimer's disease in a memory clinic

Building on previous studies that report thinning of the macula in Alzheimer’s disease (AD) and mild cognitive impairment (MCI) patients, the use of optical coherence tomography (OCT) has been proposed as a potential biomarker for AD. However, other studies contradict these results. A total of 930 participants (414 cognitively healthy people, 192 with probable amnestic MCI, and 324 probable AD patients) from a memory clinic were consecutively included in this study and underwent a spectral domain OCT scan (Maestro, Topcon) to assess total macular volume and thickness. Macular width measurements were also taken in several subregions (central, inner, and outer rings) and in layers such as the retinal nerve fiber (RNFL) and ganglion cell (CGL). The study employed a design of high ecological validity, with adjustment by age, education, sex, and OCT image quality. AD, MCI, and control groups did not significantly vary with regard to volume and retinal thickness in different layers. When these groups were compared, multivariate-adjusted analysis disclosed no significant differences in total (p = 0.564), CGL (p = 0.267), RNFL (p = 0.574), and macular thickness and volume (p = 0.380). The only macular regions showing significant differences were the superior (p = 0.040) and nasal (p = 0.040) sectors of the inner macular ring. However, adjustment for multiple comparisons nullified this significance. These results are not supporting existing claims for the usefulness of macular thickness as a biomarker of cognitive impairment in a memory unit. OCT biomarkers for AD should be subject to further longitudinal testing.

Automated detection of age-related macular degeneration in color fundus photography: a systematic review

The rising prevalence of age-related eye diseases, particularly age-related macular degeneration, places an ever-increasing burden on health care providers. As new treatments emerge, it is necessary to develop methods for reliably assessing patients' disease status and stratifying risk of progression. The presence of drusen in the retina represents a key early feature in which size, number, and morphology are thought to correlate significantly with the risk of progression to sight-threatening age-related macular degeneration. Manual labeling of drusen on color fundus photographs by a human is labor intensive and is where automatic computerized detection would appreciably aid patient care. We review and evaluate current artificial intelligence methods and developments for the automated detection of drusen in the context of age-related macular degeneration.

Usefulness of peripapillary nerve fiber layer thickness assessed by optical coherence tomography as a biomarker for Alzheimer's disease

The use of optical coherence tomography (OCT) has been suggested as a potential biomarker for Alzheimer’s Disease based on previously reported thinning of the retinal nerve fiber layer (RNFL) in Alzheimer’s disease’s (AD) and Mild Cognitive Impairment (MCI). However, other studies have not shown such results. 930 individuals (414 cognitively healthy individuals, 192 probable amnestic MCI and 324 probable AD) attending a memory clinic were consecutively included and underwent spectral domain OCT (Maestro, Topcon) examinations to assess differences in peripapillary RNFL thickness, using a design of high ecological validity. Adjustment by age, education, sex and OCT image quality was performed. We found a non-significant decrease in mean RNFL thickness as follows: control group: 100,20 ± 14,60 µm, MCI group: 98,54 ± 14,43 µm and AD group: 96,61 ± 15,27 µm. The multivariate adjusted analysis revealed no significant differences in mean overall (p = 0.352), temporal (p = 0,119), nasal (p = 0,151), superior (p = 0,435) or inferior (p = 0,825) quadrants between AD, MCI and control groups. These results do not support the usefulness of peripapillary RNFL analysis as a marker of cognitive impairment or in discriminating between cognitive groups. The analysis of other OCT measurements in other retinal areas and layers as biomarkers for AD should be tested further.

A Graph Cut Approach to Artery/Vein Classification in Ultra-Widefield Scanning Laser Ophthalmoscopy

The classification of blood vessels into arterioles and venules is a fundamental step in the automatic investigation of retinal biomarkers for systemic diseases. In this paper, we present a novel technique for vessel classification on ultra-wide-field-of-view images of the retinal fundus acquired with a scanning laser ophthalmoscope. To the best of our knowledge, this is the first time that a fully automated artery/vein classification technique for this type of retinal imaging with no manual intervention has been presented. The proposed method exploits hand-crafted features based on local vessel intensity and vascular morphology to formulate a graph representation from which a globally optimal separation between the arterial and venular networks is computed by graph cut approach. The technique was tested on three different data sets (one publicly available and two local) and achieved an average classification accuracy of 0.883 in the largest data set.

Multi-modal and multi-vendor retina image registration

Multi-modal retinal image registration is often required to utilize the complementary information from different retinal imaging modalities. However, a robust and accurate registration is still a challenge due to the modality-varied resolution, contrast, and luminosity. In this paper, a two step registration method is proposed to address this problem. Descriptor matching on mean phase images is used to globally register images in the first step. Deformable registration based on modality independent neighbourhood descriptor (MIND) method is followed to locally refine the registration result in the second step. The proposed method is extensively evaluated on color fundus images and scanning laser ophthalmoscope (SLO) images. Both qualitative and quantitative tests demonstrate improved registration using the proposed method compared to the state-of-the-art. The proposed method produces significantly and substantially larger mean Dice coefficients compared to other methods (p<0.001). It may facilitate the measurement of corresponding features from different retinal images, which can aid in assessing certain retinal diseases.