AutoMorph: Automated Retinal Vascular Morphology Quantification Via a Deep Learning Pipeline

Longitudinal associations of retinal vessel morphology with intraocular pressure and blood pressure at follow-up visit-Findings from a Danish eye and vision cohort, Project FOREVER

PURPOSE

To characterise the retinal vasculometry of a Danish eye and vision cohort and examine associations with systolic blood pressure (BP), diastolic BP, mean arterial BP, and intraocular pressure (IOP).

DESIGN

Longitudinal study.

METHODS

The retinal vasculature of fundus images from the FOREVER (Finding Ophthalmic Risks and Evaluating the Value of Eye exams and their predictive Reliability) cohort was analysed using a fully automated image analysis program. Longitudinal associations of retinal vessel morphology at follow-up visit with IOP (baseline and follow-up) and BP (follow-up) were examined using multilevel linear regression models adjusting for age, sex and retinal vasculometry at baseline as fixed effects and person as random effect. Width measurements were additionally adjusted for the spherical equivalent.

RESULTS

A total of 2089 subjects (62% female) with a mean age of 61 (standard deviation 8) years and a mean follow-up period of 4.1 years (SD 0.6 years) were included. The mean arteriolar diameter was approximately 20% thinner than the mean venular diameter, and venules were about 21%-23% less tortuous than arterioles. BP at follow-up was associated with decreased arteriolar diameter from baseline to follow-up. After adjusting for baseline IOP, IOP at follow-up was associated with increased arteriolar tortuosity above baseline (0.59%, 95% CI 0.08-1.10, p-value 0.024).

CONCLUSION

In a Danish eye and vision cohort, variations in BP and alterations in IOP over time were associated with changes in the width and tortuosity of retinal vessels. Our findings contribute novel insights into retinal vascular alterations over time.

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.

LUNet: deep learning for the segmentation of arterioles and venules in high resolution fundus images

Objective.This study aims to automate the segmentation of retinal arterioles and venules (A/V) from digital fundus images (DFI), as changes in the spatial distribution of retinal microvasculature are indicative of cardiovascular diseases, positioning the eyes as windows to cardiovascular health.Approach.We utilized active learning to create a new DFI dataset with 240 crowd-sourced manual A/V segmentations performed by 15 medical students and reviewed by an ophthalmologist. We then developed LUNet, a novel deep learning architecture optimized for high-resolution A/V segmentation. The LUNet model features a double dilated convolutional block to widen the receptive field and reduce parameter count, alongside a high-resolution tail to refine segmentation details. A custom loss function was designed to prioritize the continuity of blood vessel segmentation.Main Results.LUNet significantly outperformed three benchmark A/V segmentation algorithms both on a local test set and on four external test sets that simulated variations in ethnicity, comorbidities and annotators.Significance.The release of the new datasets and the LUNet model (www.aimlab-technion.com/lirot-ai) provides a valuable resource for the advancement of retinal microvasculature analysis. The improvements in A/V segmentation accuracy highlight LUNet's potential as a robust tool for diagnosing and understanding cardiovascular diseases through retinal imaging.

Continuous glucose monitoring and intrapersonal variability in fasting glucose

Plasma fasting glucose (FG) levels play a pivotal role in the diagnosis of prediabetes and diabetes worldwide. Here we investigated FG values using continuous glucose monitoring (CGM) devices in nondiabetic adults aged 40-70 years. FG was measured during 59,565 morning windows of 8,315 individuals (7.16 ± 3.17 days per participant). Mean FG was 96.2 ± 12.87 mg dl-1, rising by 0.234 mg dl-1 per year with age. Intraperson, day-to-day variability expressed as FG standard deviation was 7.52 ± 4.31 mg dl-1. As there are currently no CGM-based criteria for diabetes diagnosis, we analyzed the potential implications of this variability on the classification of glycemic status based on current plasma FG-based diagnostic guidelines. Among 5,328 individuals who would have been considered to have normal FG based on the first FG measurement, 40% and 3% would have been reclassified as having glucose in the prediabetes and diabetes ranges, respectively, based on sequential measurements throughout the study. Finally, we revealed associations between mean FG and various clinical measures. Our findings suggest that careful consideration is necessary when interpreting FG as substantial intraperson variability exists and highlight the potential impact of using CGM data to refine glycemic status assessment.

Retinal Changes From Hyperopia to Myopia: Not All Diopters Are Created Equal

Purpose

To quantitatively characterize retinal changes across different quantiles of refractive error in 34,414 normal eyes of 23,064 healthy adults in the UK Biobank.

Methods

Twelve optic disc (OD), foveal and vascular parameters were derived from color fundus photographs, correcting for ocular magnification as appropriate. Quantile regression was used to test the independent associations between these parameters and spherical equivalent refraction (SER) across 34 refractive quantiles (high hyperopia to high myopia)-controlling for age, sex and corneal radius.

Results

More negative SER was nonlinearly associated with greater Euclidian (largely horizontal) OD-fovea distance, larger OD, less circular OD, more obliquely orientated OD (superior pole tilted towards the fovea), brighter fovea, lower vascular complexity, less tortuous vessels, more concave (straightened out towards the fovea) papillomacular arterial/venous arcade and wider central retinal arterioles/venules. In myopia, these parameters varied more strongly with SER as myopia increased. For example, while every standard deviation (SD) decrease in vascular complexity was associated with 0.63 D (right eye: 95% confidence interval [CI], 0.58-0.68) to 0.68 D (left eye: 95% CI, 0.63-0.73) higher myopia in the quantile corresponding to -0.60 D, it was associated with 1.61 D (right eye: 95% CI, 1.40-1.82) to 1.70 D (left eye: 95% CI, 1.56-1.84) higher myopia in the most myopic quantile. OD-fovea angle (degree of vertical separation between OD and fovea) was found to vary linearly with SER, but the magnitude was of little practical importance (less than 0.10 D variation per SD change in angle in almost all refractive quantiles) compared with the changes in OD-fovea distance.

Conclusions

Several interrelated retinal changes indicative of an increasing (nonconstant) rate of mechanical stretching are evident at the posterior pole as myopia increases. These changes also suggest that the posterior pole stretches predominantly in the temporal horizontal direction.

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.

Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images

Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has emerged as a plausible diagnostic site for AD detection owing to its anatomical connection with the brain. However, existing AI models for this purpose have yet to provide a rational explanation behind their decisions and have not been able to infer the stage of the disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granula ̲ r Neuron-le v ̲ el Expl a ̲ iner (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to directly assess the continuum of AD from the retinal imaging without the need for longitudinal or clinical evaluations. This innovative approach aims to validate retinal vasculature as a biomarker and diagnostic modality for evaluating Alzheimer's Disease. Leveraged UK Biobank cognitive tests and vascular morphological features demonstrate significant promise and effectiveness of LAVA in identifying AD stages across the progression continuum.

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.

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.

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3000 Inherited Retinal Disease Patients from the United Kingdom

Purpose

To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients.

Design

Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients.

Participants

Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019.

Methods

Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire imaging dataset.

Main Outcome Measures

Quantitative FAF imaging features including area in mm 2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively.

Results

A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM , ABCC6 , ABCA4 , RDH12 , and RPE65 , with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm 2 . The five genes with the largest hyper-AF areas were BEST1 , CDH23 , RDH12 , MYO7A , and NR2E3 , with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm 2 respectively. The five genes with largest ring areas were CDH23 , NR2E3 , CRX , EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm 2 . Vessel density was found to be highest in EFEMP1 , BEST1 , TIMP3 , RS1 , and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes ( RPGR, USH2A, RHO, EYS ) found EYS to be the fastest progressor at -0.18 mm 2 /year.

Conclusions

We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.

Progress in clinical research and applications of retinal vessel quantification technology based on fundus imaging

Retinal blood vessels are the only directly observed blood vessels in the body; changes in them can help effective assess the occurrence and development of ocular and systemic diseases. The specificity and efficiency of retinal vessel quantification technology has improved with the advancement of retinal imaging technologies and artificial intelligence (AI) algorithms; it has garnered attention in clinical research and applications for the diagnosis and treatment of common eye and related systemic diseases. A few articles have reviewed this topic; however, a summary of recent research progress in the field is still needed. This article aimed to provide a comprehensive review of the research and applications of retinal vessel quantification technology in ocular and systemic diseases, which could update clinicians and researchers on the recent progress in this field.

Deep learning predicts prevalent and incident Parkinson's disease from UK Biobank fundus imaging

Parkinson's disease is the world's fastest-growing neurological disorder. Research to elucidate the mechanisms of Parkinson's disease and automate diagnostics would greatly improve the treatment of patients with Parkinson's disease. Current diagnostic methods are expensive and have limited availability. Considering the insidious and preclinical onset and progression of the disease, a desirable screening should be diagnostically accurate even before the onset of symptoms to allow medical interventions. We highlight retinal fundus imaging, often termed a window to the brain, as a diagnostic screening modality for Parkinson's disease. We conducted a systematic evaluation of conventional machine learning and deep learning techniques to classify Parkinson's disease from UK Biobank fundus imaging. Our results suggest Parkinson's disease individuals can be differentiated from age and gender-matched healthy subjects with 68% accuracy. This accuracy is maintained when predicting either prevalent or incident Parkinson's disease. Explainability and trustworthiness are enhanced by visual attribution maps of localized biomarkers and quantified metrics of model robustness to data perturbations.

Image quality assessment of retinal fundus photographs for diabetic retinopathy in the machine learning era: a review

This study aimed to evaluate the image quality assessment (IQA) and quality criteria employed in publicly available datasets for diabetic retinopathy (DR). A literature search strategy was used to identify relevant datasets, and 20 datasets were included in the analysis. Out of these, 12 datasets mentioned performing IQA, but only eight specified the quality criteria used. The reported quality criteria varied widely across datasets, and accessing the information was often challenging. The findings highlight the importance of IQA for AI model development while emphasizing the need for clear and accessible reporting of IQA information. The study suggests that automated quality assessments can be a valid alternative to manual labeling and emphasizes the importance of establishing quality standards based on population characteristics, clinical use, and research purposes. In conclusion, image quality assessment is important for AI model development; however, strict data quality standards must not limit data sharing. Given the importance of IQA for developing, validating, and implementing deep learning (DL) algorithms, it's recommended that this information be reported in a clear, specific, and accessible way whenever possible. Automated quality assessments are a valid alternative to the traditional manual labeling process, and quality standards should be determined according to population characteristics, clinical use, and research purpose.

AI-integrated ocular imaging for predicting cardiovascular disease: advancements and future outlook

Cardiovascular disease (CVD) remains the leading cause of death worldwide. Assessing of CVD risk plays an essential role in identifying individuals at higher risk and enables the implementation of targeted intervention strategies, leading to improved CVD prevalence reduction and patient survival rates. The ocular vasculature, particularly the retinal vasculature, has emerged as a potential means for CVD risk stratification due to its anatomical similarities and physiological characteristics shared with other vital organs, such as the brain and heart. The integration of artificial intelligence (AI) into ocular imaging has the potential to overcome limitations associated with traditional semi-automated image analysis, including inefficiency and manual measurement errors. Furthermore, AI techniques may uncover novel and subtle features that contribute to the identification of ocular biomarkers associated with CVD. This review provides a comprehensive overview of advancements made in AI-based ocular image analysis for predicting CVD, including the prediction of CVD risk factors, the replacement of traditional CVD biomarkers (e.g., CT-scan measured coronary artery calcium score), and the prediction of symptomatic CVD events. The review covers a range of ocular imaging modalities, including colour fundus photography, optical coherence tomography, and optical coherence tomography angiography, and other types of images like external eye images. Additionally, the review addresses the current limitations of AI research in this field and discusses the challenges associated with translating AI algorithms into clinical practice.

Genome-wide association studies and polygenic risk score phenome-wide association studies across complex phenotypes in the human phenotype project

BACKGROUND

Genome-wide association studies (GWASs) associate phenotypes and genetic variants across a study cohort. GWASs require large-scale cohorts with both phenotype and genetic sequencing data, limiting studied phenotypes. The Human Phenotype Project is a longitudinal study that has measured a wide range of clinical and biomolecular features from a self-assignment cohort over 5 years. The phenotypes collected are quantitative traits, providing higher-resolution insights into the genetics of complex phenotypes.

METHODS

We present the results of GWASs and polygenic risk score phenome-wide association studies with 729 clinical phenotypes and 4,043 molecular features from the Human Phenotype Project. This includes clinical traits that have not been previously associated with genetics, including measures from continuous sleep monitoring, continuous glucose monitoring, liver ultrasound, hormonal status, and fundus imaging.

FINDINGS

In GWAS of 8,706 individuals, we found significant associations between 169 clinical traits and 1,184 single-nucleotide polymorphisms. We found genes associated with both glycemic control and mental disorders, and we quantify the strength of genetic signals in serum metabolites. In polygenic risk score phenome-wide association studies for clinical traits, we found 16,047 significant associations.

CONCLUSIONS

The entire set of findings, which we disseminate publicly, provides newfound resolution into the genetic architecture of complex human phenotypes.

FUNDING

E.S. is supported by the Minerva foundation with funding from the Federal German Ministry for Education and Research and by the European Research Council and the Israel Science Foundation.

Interpretable Detection of Diabetic Retinopathy, Retinal Vein Occlusion, Age-Related Macular Degeneration, and Other Fundus Conditions

Diabetic retinopathy (DR), retinal vein occlusion (RVO), and age-related macular degeneration (AMD) pose significant global health challenges, often resulting in vision impairment and blindness. Automatic detection of these conditions is crucial, particularly in underserved rural areas with limited access to ophthalmic services. Despite remarkable advancements in artificial intelligence, especially convolutional neural networks (CNNs), their complexity can make interpretation difficult. In this study, we curated a dataset consisting of 15,089 color fundus photographs (CFPs) obtained from 8110 patients who underwent fundus fluorescein angiography (FFA) examination. The primary objective was to construct integrated models that merge CNNs with an attention mechanism. These models were designed for a hierarchical multilabel classification task, focusing on the detection of DR, RVO, AMD, and other fundus conditions. Furthermore, our approach extended to the detailed classification of DR, RVO, and AMD according to their respective subclasses. We employed a methodology that entails the translation of diagnostic information obtained from FFA results into CFPs. Our investigation focused on evaluating the models' ability to achieve precise diagnoses solely based on CFPs. Remarkably, our models showcased improvements across diverse fundus conditions, with the ConvNeXt-base + attention model standing out for its exceptional performance. The ConvNeXt-base + attention model achieved remarkable metrics, including an area under the receiver operating characteristic curve (AUC) of 0.943, a referable F1 score of 0.870, and a Cohen's kappa of 0.778 for DR detection. For RVO, it attained an AUC of 0.960, a referable F1 score of 0.854, and a Cohen's kappa of 0.819. Furthermore, in AMD detection, the model achieved an AUC of 0.959, an F1 score of 0.727, and a Cohen's kappa of 0.686. Impressively, the model demonstrated proficiency in subclassifying RVO and AMD, showcasing commendable sensitivity and specificity. Moreover, our models enhanced interpretability by visualizing attention weights on fundus images, aiding in the identification of disease findings. These outcomes underscore the substantial impact of our models in advancing the detection of DR, RVO, and AMD, offering the potential for improved patient outcomes and positively influencing the healthcare landscape.

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.

Multi-head deep learning framework for pulmonary disease detection and severity scoring with modified progressive learning

Chest X-rays (CXR) are the most commonly used imaging methodology in radiology to diagnose pulmonary diseases with close to 2 billion CXRs taken every year. The recent upsurge of COVID-19 and its variants accompanied by pneumonia and tuberculosis can be fatal in some cases and lives could be saved through early detection and appropriate intervention for the advanced cases. Thus CXRs can be used for an automated severity grading of pulmonary diseases that can aid radiologists in making better and informed diagnoses. In this article, we propose a single framework for disease classification and severity scoring produced by segmenting the lungs into six regions. We present a modified progressive learning technique in which the amount of augmentations at each step is capped. Our base network in the framework is first trained using modified progressive learning and can then be tweaked for new data sets. Furthermore, the segmentation task makes use of an attention map generated within and by the network itself. This attention mechanism allows to achieve segmentation results that are on par with networks having an order of magnitude or more parameters. We also propose severity score grading for 4 thoracic diseases that can provide a single-digit score corresponding to the spread of opacity in different lung segments with the help of radiologists. The proposed framework is evaluated using the BRAX data set for segmentation and classification into six classes with severity grading for a subset of the classes. On the BRAX validation data set, we achieve F1 scores of 0.924 and 0.939 without and with fine-tuning, respectively. A mean matching score of 80.8% is obtained for severity score grading while an average area under receiver operating characteristic curve of 0.88 is achieved for classification.

Ethnicity is not biology: retinal pigment score to evaluate biological variability from ophthalmic imaging using machine learning

Background

Few metrics exist to describe phenotypic diversity within ophthalmic imaging datasets, with researchers often using ethnicity as an inappropriate marker for biological variability.

Methods

We derived a continuous, measured metric, the retinal pigment score (RPS), that quantifies the degree of pigmentation from a colour fundus photograph of the eye. RPS was validated using two large epidemiological studies with demographic and genetic data (UK Biobank and EPIC-Norfolk Study).

Findings

A genome-wide association study (GWAS) of RPS from UK Biobank identified 20 loci with known associations with skin, iris and hair pigmentation, of which 8 were replicated in the EPIC-Norfolk cohort. There was a strong association between RPS and ethnicity, however, there was substantial overlap between each ethnicity and the respective distributions of RPS scores.

Interpretation

RPS serves to decouple traditional demographic variables, such as ethnicity, from clinical imaging characteristics. RPS may serve as a useful metric to quantify the diversity of the training, validation, and testing datasets used in the development of AI algorithms to ensure adequate inclusion and explainability of the model performance, critical in evaluating all currently deployed AI models. The code to derive RPS is publicly available at: https://github.com/uw-biomedical-ml/retinal-pigmentation-score.

Funding

The authors did not receive support from any organisation for the submitted work.

Association Between Retinal Features From Multimodal Imaging and Schizophrenia

Importance

The potential association of schizophrenia with distinct retinal changes is of clinical interest but has been challenging to investigate because of a lack of sufficiently large and detailed cohorts.

Objective

To investigate the association between retinal biomarkers from multimodal imaging (oculomics) and schizophrenia in a large real-world population.

Design, Setting, and Participants

This cross-sectional analysis used data from a retrospective cohort of 154 830 patients 40 years and older from the AlzEye study, which linked ophthalmic data with hospital admission data across England. Patients attended Moorfields Eye Hospital, a secondary care ophthalmic hospital with a principal central site, 4 district hubs, and 5 satellite clinics in and around London, United Kingdom, and had retinal imaging during the study period (January 2008 and April 2018). Data were analyzed from January 2022 to July 2022.

Main Outcomes and Measures

Retinovascular and optic nerve indices were computed from color fundus photography. Macular retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (mGC-IPL) thicknesses were extracted from optical coherence tomography. Linear mixed-effects models were used to examine the association between schizophrenia and retinal biomarkers.

Results

A total of 485 individuals (747 eyes) with schizophrenia (mean [SD] age, 64.9 years [12.2]; 258 [53.2%] female) and 100 931 individuals (165 400 eyes) without schizophrenia (mean age, 65.9 years [13.7]; 53 253 [52.8%] female) were included after images underwent quality control and potentially confounding conditions were excluded. Individuals with schizophrenia were more likely to have hypertension (407 [83.9%] vs 49 971 [48.0%]) and diabetes (364 [75.1%] vs 28 762 [27.6%]). The schizophrenia group had thinner mGC-IPL (-4.05 μm, 95% CI, -5.40 to -2.69; P = 5.4 × 10-9), which persisted when investigating only patients without diabetes (-3.99 μm; 95% CI, -6.67 to -1.30; P = .004) or just those 55 years and younger (-2.90 μm; 95% CI, -5.55 to -0.24; P = .03). On adjusted analysis, retinal fractal dimension among vascular variables was reduced in individuals with schizophrenia (-0.14 units; 95% CI, -0.22 to -0.05; P = .001), although this was not present when excluding patients with diabetes.

Conclusions and Relevance

In this study, patients with schizophrenia had measurable differences in neural and vascular integrity of the retina. Differences in retinal vasculature were mostly secondary to the higher prevalence of diabetes and hypertension in patients with schizophrenia. The role of retinal features as adjunct outcomes in patients with schizophrenia warrants further investigation.

CGMap: Characterizing continuous glucose monitor data in thousands of non-diabetic individuals

Despite its rising prevalence, diabetes diagnosis still relies on measures from blood tests. Technological advances in continuous glucose monitoring (CGM) devices introduce a potential tool to expand our understanding of glucose control and variability in people with and without diabetes. Yet CGM data have not been characterized in large-scale healthy cohorts, creating a lack of reference for CGM data research. Here we present CGMap, a characterization of CGM data collected from over 7,000 non-diabetic individuals, aged 40-70 years, between 2019 and 2022. We provide reference values of key CGM-derived clinical measures that can serve as a tool for future CGM research. We further explored the relationship between CGM-derived measures and diabetes-related clinical parameters, uncovering several significant relationships, including associations of mean blood glucose with measures from fundus imaging and sleep monitoring. These findings offer novel research directions for understanding the influence of glucose levels on various aspects of human health.

Quantitative Analysis of Vascular Abnormalities in Full-Term Infants With Mild Familial Exudative Vitreoretinopathy

Purpose

Our goal was to build a system that combined deep convolutional neural networks (DCNNs) and feature extraction algorithms, which automatically extracted and quantified vascular abnormalities in posterior pole retinal images of full-term infants clinically diagnosed with mild familial exudative retinopathy (FEVR).

Methods

Using posterior pole retinal images taken from 4628 full-term infants with a total of 9256 eyes, we created data sets, trained DCNNs, and performed tests and comparisons. With the segmented images, our system extracted peripapillary vascular densities, mean tortuosities, and maximum diameter ratios within the region of interest. We also compared them with normal eyes statistically.

Results

In the test data set, the trained system obtained a sensitivity of 0.78 and a specificity of 0.98 for vascular segmentation, with 0.94 and 0.99 for optic disc, respectively. While in the comparison data set, compared with normal, we found a significant increase in vascular densities in retinal images with mild FEVR (5.3211% ± 0.7600% vs. 4.5998% ± 0.6586%) and a significant increase in the maximum diameter ratios (1.8805 ± 0.3197 vs. 1.5087 ± 0.2877), while the mean tortuosities significantly decreased (2.1018 ± 0.2933 [104 cm-3] vs. 3.3344 ± 0.3890 [104 cm-3]). All values were statistically significantly different.

Conclusions

Our system could automatically segment the posterior pole retinal images and extract from vascular features associated with mild FEVR. Quantitative analysis of these parameters may help ophthalmologists in the early detection of FEVR.

Translational Relevance

This system may contribute to the early detection of FEVR and facilitate the promotion of artificial intelligence-assisted diagnostic techniques in clinical applications.

Evaluation of Microvascular Rarefaction in Vascular Cognitive Impairment and Heart Failure (CRUCIAL): Study Protocol for an Observational Study

INTRODUCTION

Microvascular rarefaction, the functional reduction in perfused microvessels and structural reduction of microvascular density, seems to be an important mechanism in the pathophysiology of small blood vessel-related disorders including vascular cognitive impairment (VCI) due to cerebral small vessel disease and heart failure with preserved ejection fraction (HFpEF). Both diseases share common risk factors including hypertension, diabetes mellitus, obesity, and ageing; in turn, these comorbidities are associated with microvascular rarefaction. Our consortium aims to investigate novel non-invasive tools to quantify microvascular health and rarefaction in both organs, as well as surrogate biomarkers for cerebral and/or cardiac rarefaction (via sublingual capillary health, vascular density of the retina, and RNA content of circulating extracellular vesicles), and to determine whether microvascular density relates to disease severity.

METHODS

The clinical research program of CRUCIAL consists of four observational cohort studies. We aim to recruit 75 VCI patients, 60 HFpEF patients, 60 patients with severe aortic stenosis (AS) undergoing surgical aortic valve replacement as a pressure overload HFpEF model, and 200 elderly participants with mixed comorbidities to serve as controls. Data collected will include medical history, physical examination, cognitive testing, advanced brain and cardiac MRI, ECG, echocardiography, sublingual capillary health, optical coherence tomography angiography (OCTa), extracellular vesicles RNA analysis, and myocardial remodelling-related serum biomarkers. The AS cohort undergoing surgery will also have myocardial biopsy for histological microvascular assessment.

DISCUSSION

CRUCIAL will examine the pathophysiological role of microvascular rarefaction in VCI and HFpEF using advanced brain and cardiac MRI techniques. Furthermore, we will investigate surrogate biomarkers for non-invasive, faster, easier, and cheaper assessment of microvascular density since these are more likely to be disseminated into widespread clinical practice. If microvascular rarefaction is an early marker of developing small vessel diseases, then measuring rarefaction may allow preclinical diagnosis, with implications for screening, risk stratification, and prevention. Further knowledge of the relevance of microvascular rarefaction and its underlying mechanisms may provide new avenues for research and therapeutic targets.