A foundation model for generalizable disease detection from retinal images.

Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders1. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications2. Here, we present RETFound, a foundation model for retinal images that learns generalizable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in several applications. Specifically, RETFound is trained on 1.6 million unlabelled retinal images by means of self-supervised learning and then adapted to disease detection tasks with explicit labels. We show that adapted RETFound consistently outperforms several comparison models in the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction with fewer labelled data. RETFound provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinical AI applications from retinal imaging.

Visual dysfunction is a better predictor than retinal thickness for dementia in Parkinson's disease.

BACKGROUND: Dementia is a common and devastating symptom of Parkinson's disease (PD). Visual function and retinal structure are both emerging as potentially predictive for dementia in Parkinson's but lack longitudinal evidence. METHODS: We prospectively examined higher order vision (skew tolerance and biological motion) and retinal thickness (spectral domain optical coherence tomography) in 100 people with PD and 29 controls, with longitudinal cognitive assessments at baseline, 18 months and 36 months. We examined whether visual and retinal baseline measures predicted longitudinal cognitive scores using linear mixed effects models and whether they predicted onset of dementia, death and frailty using time-to-outcome methods. RESULTS: Patients with PD with poorer baseline visual performance scored lower on a composite cognitive score (ß=0.178, SE=0.05, p=0.0005) and showed greater decreases in cognition over time (ß=0.024, SE=0.001, p=0.013). Poorer visual performance also predicted greater probability of dementia (χ² (1)=5.2, p=0.022) and poor outcomes (χ² (1) =10.0, p=0.002). Baseline retinal thickness of the ganglion cell-inner plexiform layer did not predict cognitive scores or change in cognition with time in PD (ß=-0.013, SE=0.080, p=0.87; ß=0.024, SE=0.001, p=0.12). CONCLUSIONS: In our deeply phenotyped longitudinal cohort, visual dysfunction predicted dementia and poor outcomes in PD. Conversely, retinal thickness had less power to predict dementia. This supports mechanistic models for Parkinson's dementia progression with onset in cortical structures and shows potential for visual tests to enable stratification for clinical trials.

Evaluating an automated machine learning model that predicts visual acuity outcomes in patients with neovascular age-related macular degeneration.

PURPOSE: Neovascular age-related macular degeneration (nAMD) is a major global cause of blindness. Whilst anti-vascular endothelial growth factor (anti-VEGF) treatment is effective, response varies considerably between individuals. Thus, patients face substantial uncertainty regarding their future ability to perform daily tasks. In this study, we evaluate the performance of an automated machine learning (AutoML) model which predicts visual acuity (VA) outcomes in patients receiving treatment for nAMD, in comparison to a manually coded model built using the same dataset. Furthermore, we evaluate model performance across ethnic groups and analyse how the models reach their predictions. METHODS: Binary classification models were trained to predict whether patients' VA would be 'Above' or 'Below' a score of 70 one year after initiating treatment, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The AutoML model was built using the Google Cloud Platform, whilst the bespoke model was trained using an XGBoost framework. Models were compared and analysed using the What-if Tool (WIT), a novel model-agnostic interpretability tool. RESULTS: Our study included 1631 eyes from patients attending Moorfields Eye Hospital. The AutoML model (area under the curve [AUC], 0.849) achieved a highly similar performance to the XGBoost model (AUC, 0.847). Using the WIT, we found that the models over-predicted negative outcomes in Asian patients and performed worse in those with an ethnic category of Other. Baseline VA, age and ethnicity were the most important determinants of model predictions. Partial dependence plot analysis revealed a sigmoidal relationship between baseline VA and the probability of an outcome of 'Above'. CONCLUSION: We have described and validated an AutoML-WIT pipeline which enables clinicians with minimal coding skills to match the performance of a state-of-the-art algorithm and obtain explainable predictions.

Quantitative Analysis of OCT for Neovascular Age-Related Macular Degeneration Using Deep Learning.

PURPOSE: To apply a deep learning algorithm for automated, objective, and comprehensive quantification of OCT scans to a large real-world dataset of eyes with neovascular age-related macular degeneration (AMD) and make the raw segmentation output data openly available for further research. DESIGN: Retrospective analysis of OCT images from the Moorfields Eye Hospital AMD Database. PARTICIPANTS: A total of 2473 first-treated eyes and 493 second-treated eyes that commenced therapy for neovascular AMD between June 2012 and June 2017. METHODS: A deep learning algorithm was used to segment all baseline OCT scans. Volumes were calculated for segmented features such as neurosensory retina (NSR), drusen, intraretinal fluid (IRF), subretinal fluid (SRF), subretinal hyperreflective material (SHRM), retinal pigment epithelium (RPE), hyperreflective foci (HRF), fibrovascular pigment epithelium detachment (fvPED), and serous PED (sPED). Analyses included comparisons between first- and second-treated eyes by visual acuity (VA) and race/ethnicity and correlations between volumes. MAIN OUTCOME MEASURES: Volumes of segmented features (mm3) and central subfield thickness (CST) (µm). RESULTS: In first-treated eyes, the majority had both IRF and SRF (54.7%). First-treated eyes had greater volumes for all segmented tissues, with the exception of drusen, which was greater in second-treated eyes. In first-treated eyes, older age was associated with lower volumes for RPE, SRF, NSR, and sPED; in second-treated eyes, older age was associated with lower volumes of NSR, RPE, sPED, fvPED, and SRF. Eyes from Black individuals had higher SRF, RPE, and serous PED volumes compared with other ethnic groups. Greater volumes of the majority of features were associated with worse VA. CONCLUSIONS: We report the results of large-scale automated quantification of a novel range of baseline features in neovascular AMD. Major differences between first- and second-treated eyes, with increasing age, and between ethnicities are highlighted. In the coming years, enhanced, automated OCT segmentation may assist personalization of real-world care and the detection of novel structure-function correlations. These data will be made publicly available for replication and future investigation by the AMD research community.

Clinician-driven artificial intelligence in ophthalmology: resources enabling democratization.

PURPOSE OF REVIEW: This article aims to discuss the current state of resources enabling the democratization of artificial intelligence (AI) in ophthalmology. RECENT FINDINGS: Open datasets, efficient labeling techniques, code-free automated machine learning (AutoML) and cloud-based platforms for deployment are resources that enable clinicians with scarce resources to drive their own AI projects. SUMMARY: Clinicians are the use-case experts who are best suited to drive AI projects tackling patient-relevant outcome measures. Taken together, open datasets, efficient labeling techniques, code-free AutoML and cloud platforms break the barriers for clinician-driven AI. As AI becomes increasingly democratized through such tools, clinicians and patients stand to benefit greatly.

Contrast-Enhanced Ultrasound Algorithms (CEUS-LIRADS/ESCULAP) for the Noninvasive Diagnosis of Hepatocellular Carcinoma - A Prospective Multicenter DEGUM Study.

BACKGROUND: This prospective multicenter study funded by the DEGUM assesses the diagnostic accuracy of standardized contrast-enhanced ultrasound (CEUS) for the noninvasive diagnosis of hepatocellular carcinoma (HCC) in high-risk patients. METHODS: Patients at high risk for HCC with a histologically proven focal liver lesion on B-mode ultrasound were recruited prospectively in a multicenter approach. Clinical and imaging data were entered via online entry forms. The diagnostic accuracies for the noninvasive diagnosis of HCC were compared for the conventional interpretation of standardized CEUS at the time of the examination (= CEUS on-site) and the two CEUS algorithms ESCULAP (Erlanger Synopsis for Contrast-enhanced Ultrasound for Liver lesion Assessment in Patients at risk) and CEUS LI-RADS (Contrast-Enhanced UltraSound Liver Imaging Reporting and Data System). RESULTS: 321 patients were recruited in 43 centers; 299 (93.1 %) had liver cirrhosis. The diagnosis according to histology was HCC in 256 cases, and intrahepatic cholangiocarcinoma (iCCA) in 23 cases. In the subgroup of cirrhotic patients (n = 299), the highest sensitivity for the diagnosis of HCC was achieved with the CEUS algorithm ESCULAP (94.2 %) and CEUS on-site (90.9 %). The lowest sensitivity was reached with the CEUS LI-RADS algorithm (64 %; p < 0.001). However, the specificity of CEUS LI-RADS (78.9 %) was superior to that of ESCULAP (50.9 %) and CEUS on-site (64.9 %; p < 0.001). At the same time, the negative predictive value (NPV) of CEUS LI-RADS was significantly inferior to that of ESCULAP (34.1 % vs. 67.4 %; p < 0.001) and CEUS on-site (62.7 %; p < 0.001). The positive predictive values of all modalities were high (around 90 %), with the best results seen for CEUS LI-RADS and CEUS on-site. CONCLUSION: This is the first multicenter, prospective comparison of standardized CEUS and the recently developed CEUS-based algorithms in histologically proven liver lesions in cirrhotic patients. Our results reaffirm the excellent diagnostic accuracy of CEUS for the noninvasive diagnosis of HCC in high-risk patients. However, on-site diagnosis by an experienced examiner achieves an almost equal diagnostic accuracy compared to CEUS-based diagnostic algorithms.

Intragraft gene expression in native kidney BK virus nephropathy versus T cell-mediated rejection: Prospects for molecular diagnosis and risk prediction.

Novel tools are needed to improve diagnostic accuracy and risk prediction in BK virus nephropathy (BKVN). We assessed the utility of intragraft gene expression testing for these purposes. Eight hundred genes were measured in 110 archival samples, including a discovery cohort of native kidney BKVN (n = 5) vs pure T cell-mediated rejection (TCMR; n = 10). Five polyomavirus genes and seven immune-related genes (five associated with BKVN and two associated with TCMR) were significantly differentially expressed between these entities (FDR < 0.05). These three sets of genes were further evaluated in samples representing a spectrum of BK infection (n = 25), followed by a multicenter validation cohort of allograft BKVN (n = 60) vs TCMR (n = 10). Polyomavirus 5-gene set expression reliably distinguished BKVN from TCMR (validation cohort AUC = 0.992), but the immune gene sets demonstrated suboptimal diagnostic performance (AUC ≤ 0.720). Within the validation cohort, no significant differences in index biopsy gene expression were identified between BKVN patients demonstrating resolution (n = 35), persistent infection (n = 14) or de novo rejection (n = 11) 6 months following a standardized reduction in immunosuppression. These results suggest that, while intragraft polyomavirus gene expression may be useful as an ancillary diagnostic for BKVN, assessment for concurrent TCMR and prediction of clinical outcome may not be feasible with current molecular tools.

Transcorneal Electrical Stimulation for the Treatment of Retinitis Pigmentosa: A Multicenter Safety Study of the OkuStim® System (TESOLA-Study).

BACKGROUND: Transcorneal electrical stimulation (TES) has been suggested as a possible treatment for retinitis pigmentosa (RP). OBJECTIVE: To expand the safety assessment of repeated applications of an electrical current from a DTL-like electrode in patients with RP. METHODS: This single-arm open label interventional safety trial included a total of 105 RP patients from 11 European centers, who received weekly TES for 6 months on 1 eye followed by observation for another 6 months without stimulation. The primary outcome measure was safety, indicated by the frequency and severity of adverse events. Secondary measures included intraocular pressure and central retinal thickness. Visual field and visual acuity were examined using the methods available at each site. RESULTS: Dry eye sensation was the most common adverse event recorded (37.5%). Serious adverse events secondary to TES were not observed. Most adverse events were mild and all resolved without sequelae. The secondary outcome measures revealed no significant or clinically relevant changes. CONCLUSION: The present results confirm the excellent safety profile of TES. Transient dry eye symptoms were the most common adverse event.

Ex vivo perfusion induces a time- and perfusate-dependent molecular repair response in explanted porcine lungs.

Ex vivo lung perfusion (EVLP) shows promise in ameliorating pretransplant acute lung injury (ALI) and expanding the donor organ pool, but the mechanisms of ex vivo repair remain poorly understood. We aimed to assess the utility of gene expression for characterizing ALI during EVLP. One hundred sixty-nine porcine lung samples were collected in vivo (n = 25), after 0 (n = 11) and 12 (n = 11) hours of cold static preservation (CSP), and after 0 (n = 57), 6 (n = 8), and 12 (n = 57) hours of EVLP, utilizing various ventilation and perfusate strategies. The expression of 53 previously described ALI-related genes was measured and correlated with function and histology. Twenty-eight genes were significantly upregulated and 6 genes downregulated after 12 hours of EVLP. Aggregate gene sets demonstrated differential expression with EVLP (P < .001) but not CSP. Upregulated 28-gene set expression peaked after 6 hours of EVLP, whereas downregulated 6-gene set expression continued to decline after 12 hours. Cellular perfusates demonstrated a greater reduction in downregulated 6-gene set expression vs acellular perfusate (P < .038). Gene set expression correlated with relevant functional and histologic parameters, including P/F ratio (P < .001) and interstitial inflammation (P < .005). Further studies with posttransplant results are warranted to evaluate the clinical significance of this novel molecular approach for assessing organ quality during EVLP.

Expression of Psoriasin in Human Papillomavirus-Induced Cervical High-Grade Squamous Intraepithelial Lesions.

OBJECTIVES: Persistent infection with human papillomavirus causes cervical high-grade squamous intraepithelial lesions (HSILs). The role of antimicrobial peptides (AMPs) in premalignant and malignant transformation is not fully understood. In this study, we examined the expression of human ß-defensin 1 (HBD-1), HBD-2, HBD-3, LL37, psoriasin, and interleukin 8 (IL-8) in women with HSIL before and 6 months after surgery. MATERIALS AND METHODS: Biopsies and secretion samples from the cervical canal were collected from 19 patients with HSIL and 14 healthy controls. The mRNA expression of HBD-1, HBD-2, HBD-3, LL37, psoriasin, and IL-8 was analyzed before and 6 months after surgery excision using reverse transcriptase real time polymerase chain reaction. For protein analyses, ELISA and immunohistochemistry were used for psoriasin and ELISA for IL-8. RESULTS: The mRNA expression of psoriasin was lower in patients before treatment compared with healthy controls (p = .05). After surgery, when the infection was cleared, psoriasin increased on mRNA (p = .04) and protein (p = .03) levels compared with before treatment. Immunostaining for psoriasin after treatment was prominent and localized in the cytoplasm of the epithelial cells. After treatment, IL-8 mRNA was reduced compared with before treatment (p = .05), but not on the protein level. No changes in mRNA expression of the other AMPs analyzed were observed in pretreatment and posttreatment samples. CONCLUSIONS: In this study of AMP expression in human papillomavirus-induced HSIL, we observed lower psoriasin levels before surgery compared with after treatment, when both mRNA and protein levels were similar to healthy controls. Interleukin 8, on the other hand, was increased before treatment, indicating an inflammatory response.

The Role of Botulinum Toxin in the Management of Ophthalmoplegia Secondary to Miller Fisher Syndrome.

Miller Fisher syndrome is an acute demyelinating polyneuropathy classically presenting with ataxia, areflexia, and ophthalmoplegia. The authors report the case of a 27-year-old female, who presented with limb weakness and double vision following a prodromal pharyngitis. Ophthalmic examination revealed fluctuant ophthalmoplegia eventually consistent with bilateral sixth cranial nerve palsies, prompting investigation for anti-ganglioside antibodies, which returned positive. Due to disabling diplopia, the patient was treated with botulinum toxin, with a resulting favourable reduction in the size of strabismus. Four months following her presentation, the patient was orthophoric and resumed normal activities.

Characterization of nanoparticle mediated laser transfection by femtosecond laser pulses for applications in molecular medicine.

BACKGROUND: In molecular medicine, the manipulation of cells is prerequisite to evaluate genes as therapeutic targets or to transfect cells to develop cell therapeutic strategies. To achieve these purposes it is essential that given transfection techniques are capable of handling high cell numbers in reasonable time spans. To fulfill this demand, an alternative nanoparticle mediated laser transfection method is presented herein. The fs-laser excitation of cell-adhered gold nanoparticles evokes localized membrane permeabilization and enables an inflow of extracellular molecules into cells. RESULTS: The parameters for an efficient and gentle cell manipulation are evaluated in detail. Efficiencies of 90% with a cell viability of 93% were achieved for siRNA transfection. The proof for a molecular medical approach is demonstrated by highly efficient knock down of the oncogene HMGA2 in a rapidly proliferating prostate carcinoma in vitro model using siRNA. Additionally, investigations concerning the initial perforation mechanism are conducted. Next to theoretical simulations, the laser induced effects are experimentally investigated by spectrometric and microscopic analysis. The results indicate that near field effects are the initial mechanism of membrane permeabilization. CONCLUSION: This methodical approach combined with an automated setup, allows a high throughput targeting of several 100,000 cells within seconds, providing an excellent tool for in vitro applications in molecular medicine. NIR fs lasers are characterized by specific advantages when compared to lasers employing longer (ps/ns) pulses in the visible regime. The NIR fs pulses generate low thermal impact while allowing high penetration depths into tissue. Therefore fs lasers could be used for prospective in vivo applications.

Associations between unilateral amblyopia in childhood and cardiometabolic disorders in adult life: a cross-sectional and longitudinal analysis of the UK Biobank.

Background: Amblyopia is a common neurodevelopmental condition and leading cause of childhood visual impairment. Given the known association between neurodevelopmental impairment and cardiometabolic dysfunction in later life, we investigated whether children with amblyopia have increased risk of cardiometabolic disorders in adult life. Methods: This was a cross-sectional and longitudinal analysis of 126,399 United Kingdom Biobank cohort participants who underwent ocular examination. A subset of 67,321 of these received retinal imaging. Data analysis was conducted between November 1st 2021 and October 15th 2022. Our primary objective was to investigate the association between amblyopia and a number of components of metabolic syndrome and individual cardiometabolic diseases. Childhood amblyopia, dichotomised as resolved or persisting by adulthood, cardiometabolic disease and mortality were defined using ophthalmic assessment, self-reported, hospital admissions and death records. Morphological features of the optic nerve and retinal vasculature and sublayers were extracted from retinal photography and optical coherence tomography. Associations between amblyopia and cardiometabolic disorders as well as retinal markers were investigated in multivariable-adjusted regression models. Findings: Individuals with persisting amblyopia (n = 2647) were more likely to be obese (adjusted odds ratio (95% confidence interval): 1.16 (1.05; 1.28)), hypertensive (1.25 (1.13; 1.38)) and diabetic (1.29 (1.04; 1.59)) than individuals without amblyopia (controls, (n = 18,481)). Amblyopia was also associated with an increased risk of myocardial infarction (adjusted hazard ratio: 1.38 (1.11; 1.72)) and death (1.36 (1.15; 1.60)). On retinal imaging, amblyopic eyes had significantly increased venular caliber (0.29 units (0.21; 0.36)), increased tortuosity (0.11 units (0.03; 0.19)), but lower fractal dimension (-0.23 units (-0.30; -0.16)) and thinner ganglion cell-inner plexiform layer (mGC-IPL, -2.85 microns (-3.47; -2.22)). Unaffected fellow eyes of individuals with amblyopia also had significantly lower retinal fractal dimension (-0.08 units (-0.15; -0.01)) and thinner mGC-IPL (-1.14 microns (-1.74; -0.54)). Amblyopic eyes with a persisting visual deficit had smaller optic nerve disc height (-0.17 units (-0.25; -0.08)) and width (-0.13 units (-0.21; -0.04)) compared to control eyes. Interpretation: Although further research is needed to understand the basis of the observed associations, healthcare professionals should be cognisant of greater cardiometabolic dysfunction in adults who had childhood amblyopia. Differences in retinal features in both the amblyopic eye and the unaffected non-amblyopic suggest generalised versus local processes. Funding: Medical Research Council (MR/T000953/1) and the National Institute for Health and Care Research.

Oculomics: A Crusade Against the Four Horsemen of Chronic Disease.

Chronic, non-communicable diseases present a major barrier to living a long and healthy life. In many cases, early diagnosis can facilitate prevention, monitoring, and treatment efforts, improving patient outcomes. There is therefore a critical need to make screening techniques as accessible, unintimidating, and cost-effective as possible. The association between ocular biomarkers and systemic health and disease (oculomics) presents an attractive opportunity for detection of systemic diseases, as ophthalmic techniques are often relatively low-cost, fast, and non-invasive. In this review, we highlight the key associations between structural biomarkers in the eye and the four globally leading causes of morbidity and mortality: cardiovascular disease, cancer, neurodegenerative disease, and metabolic disease. We observe that neurodegenerative disease is a particularly promising target for oculomics, with biomarkers detected in multiple ocular structures. Cardiovascular disease biomarkers are present in the choroid, retinal vasculature, and retinal nerve fiber layer, and metabolic disease biomarkers are present in the eyelid, tear fluid, lens, and retinal vasculature. In contrast, only the tear fluid emerged as a promising ocular target for the detection of cancer. The retina is a rich source of oculomics data, the analysis of which has been enhanced by artificial intelligence-based tools. Although not all biomarkers are disease-specific, limiting their current diagnostic utility, future oculomics research will likely benefit from combining data from various structures to improve specificity, as well as active design, development, and optimization of instruments that target specific disease signatures, thus facilitating differential diagnoses.

Long-term diseases can stop people living long and healthy lives. In many cases, early diagnosis can help to prevent, monitor, and treat disease, which can improve patients' health. In order to diagnose disease, we need tools that are easy for patients to access, painless, and low-cost. The eye may provide the solution. In this review, we discuss the link between changes in the eye and four types of long-term disease that, together, kill most of the population: (1) Cardiovascular disease (affecting the heart and/or blood). (2) Cancer (abnormal growth of cells). (3) Neurodegenerative disease (affecting the brain and/or nervous system). (4) Metabolic disease (problems storing, accessing, and using the body's fuel). We show that neurodegenerative disease leaves tell-tale signs in lots of different parts of the eye. Signs of cardiovascular and metabolic disease biomarkers are mostly found in the back of the eye, and signs of cancer can be found in the tear fluid. Although signs of disease can be seen in the eye, not all of them will tell us what the disease is. We believe that future research will help us to understand more about long-term disease and how to detect it if we combine information from different structures within the eye and develop new tools to target these specific structures.

CF-Loss: Clinically-relevant feature optimised loss function for retinal multi-class vessel segmentation and vascular feature measurement.

Characterising clinically-relevant vascular features, such as vessel density and fractal dimension, can benefit biomarker discovery and disease diagnosis for both ophthalmic and systemic diseases. In this work, we explicitly encode vascular features into an end-to-end loss function for multi-class vessel segmentation, categorising pixels into artery, vein, uncertain pixels, and background. This clinically-relevant feature optimised loss function (CF-Loss) regulates networks to segment accurate multi-class vessel maps that produce precise vascular features. Our experiments first verify that CF-Loss significantly improves both multi-class vessel segmentation and vascular feature estimation, with two standard segmentation networks, on three publicly available datasets. We reveal that pixel-based segmentation performance is not always positively correlated with accuracy of vascular features, thus highlighting the importance of optimising vascular features directly via CF-Loss. Finally, we show that improved vascular features from CF-Loss, as biomarkers, can yield quantitative improvements in the prediction of ischaemic stroke, a real-world clinical downstream task. The code is available at https://github.com/rmaphoh/feature-loss.

Cross-modality Labeling Enables Noninvasive Capillary Quantification as a Sensitive Biomarker for Assessing Cardiovascular Risk.

Purpose: We aim to use fundus fluorescein angiography (FFA) to label the capillaries on color fundus (CF) photographs and train a deep learning model to quantify retinal capillaries noninvasively from CF and apply it to cardiovascular disease (CVD) risk assessment. Design: Cross-sectional and longitudinal study. Participants: A total of 90732 pairs of CF-FFA images from 3893 participants for segmentation model development, and 49229 participants in the UK Biobank for association analysis. Methods: We matched the vessels extracted from FFA and CF, and used vessels from FFA as labels to train a deep learning model (RMHAS-FA) to segment retinal capillaries using CF. We tested the model's accuracy on a manually labeled internal test set (FundusCapi). For external validation, we tested the segmentation model on 7 vessel segmentation datasets, and investigated the clinical value of the segmented vessels in predicting CVD events in the UK Biobank. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity for segmentation. Hazard ratio (HR; 95% confidence interval [CI]) for Cox regression analysis. Results: On the FundusCapi dataset, the segmentation performance was AUC = 0.95, accuracy = 0.94, sensitivity = 0.90, and specificity = 0.93. Smaller vessel skeleton density had a stronger correlation with CVD risk factors and incidence (P < 0.01). Reduced density of small vessel skeletons was strongly associated with an increased risk of CVD incidence and mortality for women (HR [95% CI] = 0.91 [0.84-0.98] and 0.68 [0.54-0.86], respectively). Conclusions: Using paired CF-FFA images, we automated the laborious manual labeling process and enabled noninvasive capillary quantification from CF, supporting its potential as a sensitive screening method for identifying individuals at high risk of future CVD events. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Exploring Patient Demographics and Presence of Retinal Vascular Disease in Paracentral Acute Middle Maculopathy.

PURPOSE: To investigate the sociodemographic profile, the association with retinal vascular diseases (RVD) and systemic comorbidities, and visual outcomes of patients with paracentral acute middle maculopathy (PAMM) in a large, ethnically diverse single-center cohort. DESIGN: Retrospective cohort study. METHODS: Electronic health record query for all patients presenting with PAMM at Moorfields Eye Hospital, London, was completed. Detailed demographic, clinical, and systemic information were collected and analyzed. RESULTS: A total of 78 eyes of 78 patients with confirmed PAMM were included in the study. Forty patients (51.3%) presented with no RVD, 20 patients (25.6%) with retinal vein occlusion (RVO), 16 patients (20.5%) with retinal artery occlusion (RAO), and 2 patients (2.6%) with concomitant RAO and RVO. Patients with PAMM+RAO were older than those with RVO (P = .02) and more likely to have a history of major adverse cardiovascular events (MACE) (P = .01), with a significantly worse presenting best corrected visual acuity (BCVA) (20/50) compared to patients with RVO (P = .02) and no RVD (P < .001). Individuals with isolated PAMM had a significantly higher prevalence of previous MACE (P = .04) and sickle cell disease (SCD) (P = .04) compared to those with RVO. At the last follow-up, 64 patients (85.3%) had a good BCVA (>20/32). CONCLUSIONS: The significant association of PAMM with RVD supports the hypothesis of an ischemic etiology. Individuals with isolated PAMM had a higher prevalence of MACE and SCD. Thus, it is important to prompt immediate referral for a comprehensive systemic evaluation. Across the whole cohort, PAMM was associated with good BCVA improvement during follow-up, indicating a good visual prognosis.

Association between polygenic risk for schizophrenia and retinal morphology: A cross-sectional analysis of the United Kingdom Biobank.

We examined the relationship between genetic risk for schizophrenia (SZ), using polygenic risk scores (PRSs), and retinal morphological alterations. Retinal structural and vascular indices derived from optical coherence tomography (OCT) and color fundus photography (CFP) and PRSs for SZ were analyzed in N = 35,024 individuals from the prospective cohort study, United Kingdom Biobank (UKB). Results indicated that macular ganglion cell-inner plexiform layer (mGC-IPL) thickness was significantly inversely related to PRS for SZ, and this relationship was strongest within higher PRS quintiles and independent of potential confounders and age. PRS, however, was unrelated to retinal vascular characteristics, with the exception of venular tortuosity, and other retinal structural indices (macular retinal nerve fiber layer [mRNFL], inner nuclear layer [INL], cup-to-disc ratio [CDR]). Additionally, the association between greater PRS and reduced mGC-IPL thickness was only significant for participants in the 40-49 and 50-59 age groups, not those in the 60-69 age group. These findings suggest that mGC-IPL thinning is associated with a genetic predisposition to SZ and may reflect neurodevelopmental and/or neurodegenerative processes inherent to SZ. Retinal microvasculature alterations, however, may be secondary consequences of SZ and do not appear to be associated with a genetic predisposition to SZ.

Relationship Between Oral Health and Glaucoma Traits in the United Kingdom.

PRCIS: In this cross-sectional analysis of UK Biobank participants, we find no adverse association between self-reported oral health conditions and either glaucoma or elevated intraocular pressures. PURPOSE: Poor oral health may cause inflammation, which accelerates the progression of neurodegenerative diseases. We investigated the relationship between oral health and glaucoma. PATIENTS: United Kingdom Biobank participants. METHODS: This is a cross-sectional analysis of participants categorized by self-reported oral health status. Multivariable linear and logistic regression models were used. Primary analysis examined the association with glaucoma prevalence. Secondary analyses examined associations with IOP, macular retinal nerve fiber layer (mRNFL), and ganglion cell inner plexiform layer (mGCIPL) thicknesses, and interaction terms with multitrait glaucoma polygenic risk scores (MTAG PRS) or intraocular pressure (IOP) PRS. RESULTS: A total of 170,815 participants (34.3%) reported current oral health problems, including painful or bleeding gums, toothache, loose teeth, and/or denture wear. A In all, 33,059, 33,004, 14,652, and 14,613 participants were available for analysis of glaucoma, IOP, mRNFL, and mGCIPL, respectively. No association between oral health and glaucoma was identified [odds ratio (OR): 1.04, 95% CI: 0.95-1.14]. IOPs were slightly lower among those with oral disease (-0.08 mm Hg, 95% CI: -0.15, -0.009); specifically, among those with loose teeth ( P =0.03) and denture-wearers ( P <0.0001). mRNFL measurements were lower among those with oral health conditions (-0.14 µm, 95% CI: -0.27, -0.0009), but mGCIPL measurements ( P =0.96) were not significantly different. A PRS for IOP or glaucoma did not modify relations between oral health and IOP or glaucoma ( P for interactions ≥​​​​0.17). CONCLUSIONS: Self-reported oral health was not associated with elevated IOP or an increased risk of glaucoma. Future studies should confirm the null association between clinically diagnosed oral health conditions and glaucoma.