Retinal structural and functional changes in humans can be manifestations of different physiological or pathological conditions. Retinal imaging is the only way to directly inspect blood vessels and their pathological changes throughout the whole body non-invasively. Various quantitative analysis metrics have been used to measure the abnormalities of retinal microvasculature in the context of different retinal, cerebral and systemic disorders. Recently developed optical coherence tomography angiography (OCTA) is a non-invasive imaging tool that allows high-resolution three-dimensional mapping of the retinal microvasculature. The identification of retinal biomarkers from OCTA images could facilitate clinical investigation in various scenarios. We provide a framework for extracting computational retinal microvasculature biomarkers (CRMBs) from OCTA images through a knowledge-driven computerized automatic analytical system. Our method allows for improved identification of the foveal avascular zone (FAZ) and introduces a novel definition of vessel dispersion in the macular region. Furthermore, retinal large vessels and capillaries of the superficial and deep plexus can be differentiated, correlating with retinal pathology. The diagnostic value of OCTA CRMBs was demonstrated by a cross-sectional study with 30 healthy subjects and 43 retinal vein occlusion (RVO) patients, which identified strong correlations between OCTA CRMBs and retinal function in RVO patients. These OCTA CRMBs generated through this \"all-in-one\" pipeline may provide clinicians with insights about disease severity, treatment response and prognosis, aiding in the management and early detection of various disorders.

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

Identifying unknown types of diseases is a crucial step in preceding retinal imaging classification for the sake of safety, which is known as anomaly detection of retinal imaging. However, the widely-used supervised learning algorithms are not suitable for this problem, since the data of the unknown category is unobtainable. Moreover, for retinal imaging with different types of anomalous regions, using a single-resolution input causes information loss. Therefore, we propose an unsupervised auto-encoder model with multi-resolution inputs and outputs. We provide a theoretical understanding of the effectiveness of reconstruction error and the improvement of self-supervised learning for anomaly detection. Our experiments on two widely-used retinal imaging datasets show that the proposed methods are superior to other methods, and further experiments verify the validity of each part of the proposed method.

UNASSIGNED: We explored the longitudinal relationship between retinal vascular features and dementia incidence over 10 years.
UNASSIGNED: Among 584 participants from the Three-City-Alienor (3C-Alienor) population-based cohort, quantitative retinal vascular features (caliber, tortuosity, fractal dimension) were measured using semi-automated software. Dementia was actively diagnosed over the follow-up period.
UNASSIGNED: One hundred twenty-eight participants (21.9%) developed dementia over a median of 7.1 years. In Cox proportional hazards models adjusted for sociodemographic characteristics, apolipoprotein E (APOE) ε4, and vascular factors, increased retinal arteriolar tortuosity was associated with all-cause dementia (hazard ratio per standard deviation increase, 1.21; 95% confidence interval: 1.02-1.44). Wider retinal calibers and a higher venular tortuosity were associated with mixed/vascular dementia, but not Alzheimer\'s disease. Fractal dimensions were not associated with dementia.
UNASSIGNED: Changes in the retinal microvasculature were associated with dementia risk. More studies are needed to replicate these findings and determine which features might help identify persons at risk at an early stage.
CONCLUSIONS: The retinal microvasculature might reflect the brain microvasculatureWe explored the association between retinal vascular features and incident dementia584 participants from the Three-City-Alienor cohort were followed-up over 10 yearsIncreased arteriolar tortuosity and venular calibers were associated with dementia riskRetinal imaging might help identify persons at risk of future dementia.

Glaucoma is a chronic disorder that harms the optic nerves and causes irreversible blindness. The calculation of optic cup (OC) to optic disc (OD) ratio plays an important role in the primary screening and diagnosis of glaucoma. Thus, automatic and precise segmentations of OD and OC is highly preferable. Recently, deep neural networks demonstrate remarkable progress in the OD and OC segmentation, however, they are severely hindered in generalizing across different scanners and image resolution. In this work, we propose a novel domain adaptation-based framework to mitigate the performance degradation in OD and OC segmentation. We first devise an effective transformer-based segmentation network as a backbone to accurately segment the OD and OC regions. Then, to address the issue of domain shift, we introduce domain adaptation into the learning paradigm to encourage domain-invariant features. Since the segmentation-based domain adaptation loss is insufficient for capturing segmentation details, we further propose an auxiliary classifier to enable the discrimination on segmentation details. Exhaustive experiments on three public retinal fundus image datasets, i.e., REFUGE, Drishti-GS and RIM-ONE-r3, demonstrate our superior performance on the segmentation of OD and OC. These results suggest that our proposal has great potential to be an important component for an automated glaucoma screening system.

An ophthalmic swept source-optical coherence tomography (SS-OCT) system based on a high-speed scanning laser at 1060 nm with a scanning rate of 100 KHz is constructed. Since the sample arm of the interferometer is comprised of multiple glass materials, the ensuing dispersion severely degrades imaging quality. In this article, second-order dispersion simulation analysis for various materials was performed first, and dispersion equilibrium was implemented utilizing physical compensation methods. After dispersion compensation, an imaging depth in air of 4.013 mm was achieved in model eye experiments, and signal-to-noise ratio was enhanced by 11.6%, with a value of 53.8 dB. In vivo imaging of the human retina was performed to demonstrate structurally distinguishable retinal images, characterized by an axial resolution improvement of 19.8%, with a value of 7.7 μm close to the theoretical value of 7.5 μm. The proposed physical dispersion compensation method enhances imaging performance in SS-OCT systems, enabling visualization of several low scattering mediums.

UNASSIGNED: It has been hypothesized that abnormal microcirculation in the retina might predict the risk of ischemic damages in the brain. Direct comparison between the retinal and the cerebral microcirculation using similar animal preparation and under similar experimental conditions would help test this hypothesis.
UNASSIGNED: We investigated capillary red-blood-cell (RBC) flux changes under controlled conditions and bilateral-carotid-artery-stenosis (BCAS)-induced hypoperfusion, and then compared them with our previous measurements performed in the brain.
UNASSIGNED: We measured capillary RBC flux in mouse retina with two-photon microscopy using a fluorescence-labeled RBC-passage approach. Key physiological parameters were monitored during experiments to ensure stable physiology.
UNASSIGNED: We found that under the controlled conditions, capillary RBC flux in the retina was much higher than in the brain (i.e., cerebral cortical gray matter and subcortical white matter), and that BCAS induced a much larger decrease in capillary RBC flux in the retina than in the brain.
UNASSIGNED: We demonstrated a two-photon microscopy-based technique to efficiently measure capillary RBC flux in the retina. Since cerebral subcortical white matter often exhibits early pathological developments due to global hypoperfusion, our results suggest that retinal microcirculation may be utilized as an early marker of brain diseases involving global hypoperfusion.

Alzheimer\'s disease (AD) remains a global health challenge in the 21st century due to its increasing prevalence as the major cause of dementia. State-of-the-art artificial intelligence (AI)-based tests could potentially improve population-based strategies to detect and manage AD. Current retinal imaging demonstrates immense potential as a non-invasive screening measure for AD, by studying qualitative and quantitative changes in the neuronal and vascular structures of the retina that are often associated with degenerative changes in the brain. On the other hand, the tremendous success of AI, especially deep learning, in recent years has encouraged its incorporation with retinal imaging for predicting systemic diseases. Further development in deep reinforcement learning (DRL), defined as a subfield of machine learning that combines deep learning and reinforcement learning, also prompts the question of how it can work hand in hand with retinal imaging as a viable tool for automated prediction of AD. This review aims to discuss potential applications of DRL in using retinal imaging to study AD, and their synergistic application to unlock other possibilities, such as AD detection and prediction of AD progression. Challenges and future directions, such as the use of inverse DRL in defining reward function, lack of standardization in retinal imaging, and data availability, will also be addressed to bridge gaps for its transition into clinical use.

Currently in the United Kingdom, cardiovascular disease (CVD) risk assessment is based on the QRISK3 score, in which 10% 10-year CVD risk indicates clinical intervention. However, this benchmark has limited efficacy in clinical practice and the need for a more simple, non-invasive risk stratification tool is necessary. Retinal photography is becoming increasingly acceptable as a non-invasive imaging tool for CVD. Previously, we developed a novel CVD risk stratification system based on retinal photographs predicting future CVD risk. This study aims to further validate our biomarker, Reti-CVD, (1) to detect risk group of ≥ 10% in 10-year CVD risk and (2) enhance risk assessment in individuals with QRISK3 of 7.5-10% (termed as borderline-QRISK3 group) using the UK Biobank.
Reti-CVD scores were calculated and stratified into three risk groups based on optimized cut-off values from the UK Biobank. We used Cox proportional-hazards models to evaluate the ability of Reti-CVD to predict CVD events in the general population. C-statistics was used to assess the prognostic value of adding Reti-CVD to QRISK3 in borderline-QRISK3 group and three vulnerable subgroups.
Among 48,260 participants with no history of CVD, 6.3% had CVD events during the 11-year follow-up. Reti-CVD was associated with an increased risk of CVD (adjusted hazard ratio [HR] 1.41; 95% confidence interval [CI], 1.30-1.52) with a 13.1% (95% CI, 11.7-14.6%) 10-year CVD risk in Reti-CVD-high-risk group. The 10-year CVD risk of the borderline-QRISK3 group was greater than 10% in Reti-CVD-high-risk group (11.5% in non-statin cohort [n = 45,473], 11.5% in stage 1 hypertension cohort [n = 11,966], and 14.2% in middle-aged cohort [n = 38,941]). C statistics increased by 0.014 (0.010-0.017) in non-statin cohort, 0.013 (0.007-0.019) in stage 1 hypertension cohort, and 0.023 (0.018-0.029) in middle-aged cohort for CVD event prediction after adding Reti-CVD to QRISK3.
Reti-CVD has the potential to identify individuals with ≥ 10% 10-year CVD risk who are likely to benefit from earlier preventative CVD interventions. For borderline-QRISK3 individuals with 10-year CVD risk between 7.5 and 10%, Reti-CVD could be used as a risk enhancer tool to help improve discernment accuracy, especially in adult groups that may be pre-disposed to CVD.

Previous studies have explored the associations of retinal vessel calibre, measured from retinal photographs or fundus images using semi-automated computer programs, with cognitive impairment and dementia, supporting the concept that retinal blood vessels reflect microvascular changes in the brain. Recently, artificial intelligence deep-learning algorithms have been developed for the fully automated assessment of retinal vessel calibres. Therefore, we aimed to determine whether deep-learning-based retinal vessel calibre measurements are predictive of risk of cognitive decline and dementia. We conducted a prospective study recruiting participants from memory clinics at the National University Hospital and St. Luke\'s Hospital in Singapore; all participants had comprehensive clinical and neuropsychological examinations at baseline and annually for up to 5 years. Fully automated measurements of retinal arteriolar and venular calibres from retinal fundus images were estimated using a deep-learning system. Cox regression models were then used to assess the relationship between baseline retinal vessel calibre and the risk of cognitive decline and developing dementia, adjusting for age, gender, ethnicity, education, cerebrovascular disease status, hypertension, hyperlipidemia, diabetes, and smoking. A total of 491 participants were included in this study, of whom 254 developed cognitive decline over 5 years. In multivariable models, narrower retinal arteriolar calibre (hazard ratio per standard deviation decrease = 1.258, P = 0.008) and wider retinal venular calibre (hazard ratio per standard deviation increase = 1.204, P = 0.037) were associated with increased risk of cognitive decline. Among participants with cognitive impairment but no dementia at baseline (n = 212), 44 progressed to have incident dementia; narrower retinal arteriolar calibre was also associated with incident dementia (hazard ratio per standard deviation decrease = 1.624, P = 0.021). In summary, deep-learning-based measurement of retinal vessel calibre was associated with risk of cognitive decline and dementia.