Convolutional neural network-based classification of glaucoma using optic radiation tissue properties.

BACKGROUND: Sensory changes due to aging or disease can impact brain tissue. This study aims to investigate the link between glaucoma, a leading cause of blindness, and alterations in brain connections. METHODS: We analyzed diffusion MRI measurements of white matter tissue in a large group, consisting of 905 glaucoma patients (aged 49-80) and 5292 healthy individuals (aged 45-80) from the UK Biobank. Confounds due to group differences were mitigated by matching a sub-sample of controls to glaucoma subjects. We compared classification of glaucoma using convolutional neural networks (CNNs) focusing on the optic radiations, which are the primary visual connection to the cortex, against those analyzing non-visual brain connections. As a control, we evaluated the performance of regularized linear regression models. RESULTS: We showed that CNNs using information from the optic radiations exhibited higher accuracy in classifying subjects with glaucoma when contrasted with CNNs relying on information from non-visual brain connections. Regularized linear regression models were also tested, and showed significantly weaker classification performance. Additionally, the CNN was unable to generalize to the classification of age-group or of age-related macular degeneration. CONCLUSIONS: Our findings indicate a distinct and potentially non-linear signature of glaucoma in the tissue properties of optic radiations. This study enhances our understanding of how glaucoma affects brain tissue and opens avenues for further research into how diseases that affect sensory input may also affect brain aging.

In this study, we explored the relationship between glaucoma, the most common cause of blindness, and changes within the brain. We used data from diffusion MRI, a measurement method which assesses the properties of brain connections. We examined 905 individuals with glaucoma alongside 5292 healthy people. We refined the test cohort to be closely matched in age, sex, ethnicity, and socioeconomic backgrounds. The use of deep learning neural networks allowed accurate detection of glaucoma by focusing on the tissue properties of the optic radiations, a major brain pathway that transmits visual information, rather than other brain pathways used for comparison. Our work provides additional evidence that brain connections may age differently based on varying sensory inputs.

Sight threatening diabetic retinopathy in patients with macular telangiectasia type 2.

PURPOSE: Although diabetes is highly prevalent in patients with MacTel, progression to severe non-proliferative (NPDR) and proliferative diabetic retinopathy (PDR) is rarely reported. We report multimodal imaging features of sight-threatening diabetic retinopathy (STDR) in eyes with macular telangiectasia type 2 (MacTel). METHODS: Retrospective case series of seven participants of the MacTel Study at the Moorfields Eye Hospital NHS Foundation Trust study site and one patient from the Institute of Retina and Vitreous of Londrina, Brazil. Sight threatening diabetic retinopathy was defined as severe NPDR, PDR or diabetic macular edema. RESULTS: We report imaging features of 16 eyes of eight patients (7/8, 87.5% female) with diagnoses of MacTel and type 2 diabetes mellitus with STDR. Mean (SD) age was 56 (8.3) years. Patients were followed-up for a mean time of 9.1 (4.7) years. A total of 10/16 (62.5%) eyes showed PDR and 2/16 (12.5%) eyes presented a macular epiretinal neovascularization. CONCLUSIONS: People with diabetes mellitus and MacTel may not be protected from STDR as previously reported. Although the two diseases rarely co-exist, regular monitoring for diabetic retinopathy progression is recommended according to baseline retinopathy severity grades in line with established international guidelines. The presence of MacTel may not modify extended screening intervals, but there is no current evidence. The limited case series in the literature support treatment for complications and should follow the standard of care for either condition. Due to dual pathology, reactivation may be difficult to diagnose on standard imaging and multimodal imaging is recommended.

Retinal vessel volume reference database derived from volume-rendered optical coherence tomography angiography.

Optical coherence tomography angiography (OCTA) enables three-dimensional reconstruction of the functional blood vessels in the retina. Therefore, it enables the quantification of 3D retinal vessel parameters such as surface area and vessel volume. In spite of the widespread use of OCTA, no representative volume-rendered vessel volume (VV) data are published to date. In this study, OCTA 3 × 3 mm macular cubes were processed with volume-rendering techniques to measure VV in 203 eyes from 107 healthy volunteers. Generalized linear models (GLM) were constructed to assess the impact of age, gender, visual acuity (VA), spherical equivalent (SE), and axial length (AL) on VV. Overall mean VV was 0.23 ± 0.05mm3. Age and axial length showed a negative correlation with VV. However, GLM model analysis found that AL exerted the most pronounced influence on VV. No statistically significant associations were identified between gender or between left and right eyes. This is the first study to assess 3D OCTA VV and its naturally occurring variations in a large series of healthy subjects. It offers novel insights into the characterization of normal retinal vascular anatomy in healthy individuals, contributing to a valuable reference for future research in this field.

Artificial intelligence-supported diabetic retinopathy screening in Tanzania: rationale and design of a randomised controlled trial.

INTRODUCTION: Globally, diabetic retinopathy (DR) is a major cause of blindness. Sub-Saharan Africa is projected to see the largest proportionate increase in the number of people living with diabetes over the next two decades. Screening for DR is recommended to prevent sight loss; however, in many low and middle-income countries, because of a lack of specialist eye care staff, current screening services for DR are not optimal. The use of artificial intelligence (AI) for DR screening, which automates the grading of retinal photographs and provides a point-of-screening result, offers an innovative potential solution to improve DR screening in Tanzania. METHODS AND ANALYSIS: We will test the hypothesis that AI-supported DR screening increases the proportion of persons with true referable DR who attend the central ophthalmology clinic following referral after screening in a single-masked, parallel group, individually randomised controlled trial. Participants (2364) will be randomised (1:1 ratio) to either AI-supported or the standard of care DR screening pathway. Participants allocated to the AI-supported screening pathway will receive their result followed by point-of-screening counselling immediately after retinal image capture. Participants in the standard of care arm will receive their result and counselling by phone once the retinal images have been graded in the usual way (typically after 2-4 weeks). The primary outcome is the proportion of persons with true referable DR attending the central ophthalmology clinic within 8 weeks of screening. Secondary outcomes, by trial arm, include the proportion of persons attending the central ophthalmology clinic out of all those referred, sensitivity and specificity, number of false positive referrals, acceptability and fidelity of AI-supported screening. ETHICS AND DISSEMINATION: The London School of Hygiene & Tropical Medicine, Kilimanjaro Christian Medical Centre and Tanzanian National Institute of Medical Research ethics committees have approved the trial. The results will be submitted to peer-reviewed journals for publication. TRIAL REGISTRATION NUMBER: ISRCTN18317152.

Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading.

PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP). DESIGN: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale. PARTICIPANTS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants. METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale. MAIN OUTCOME MEASURES: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP. RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values. CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Human selection bias drives the linear nature of the more ground truth effect in explainable deep learning optical coherence tomography image segmentation.

Supervised deep learning (DL) algorithms are highly dependent on training data for which human graders are assigned, for example, for optical coherence tomography (OCT) image annotation. Despite the tremendous success of DL, due to human judgment, these ground truth labels can be inaccurate and/or ambiguous and cause a human selection bias. We therefore investigated the impact of the size of the ground truth and variable numbers of graders on the predictive performance of the same DL architecture and repeated each experiment three times. The largest training dataset delivered a prediction performance close to that of human experts. All DL systems utilized were highly consistent. Nevertheless, the DL under-performers could not achieve any further autonomous improvement even after repeated training. Furthermore, a quantifiable linear relationship between ground truth ambiguity and the beneficial effect of having a larger amount of ground truth data was detected and marked as the more-ground-truth effect.

What are the perceptions and concerns of people living with diabetes and National Health Service staff around the potential implementation of AI-assisted screening for diabetic eye disease? Development and validation of a survey for use in a secondary care screening setting.

INTRODUCTION: The English National Health Service (NHS) Diabetic Eye Screening Programme (DESP) performs around 2.3 million eye screening appointments annually, generating approximately 13 million retinal images that are graded by humans for the presence or severity of diabetic retinopathy. Previous research has shown that automated retinal image analysis systems, including artificial intelligence (AI), can identify images with no disease from those with diabetic retinopathy as safely and effectively as human graders, and could significantly reduce the workload for human graders. Some algorithms can also determine the level of severity of the retinopathy with similar performance to humans. There is a need to examine perceptions and concerns surrounding AI-assisted eye-screening among people living with diabetes and NHS staff, if AI was to be introduced into the DESP, to identify factors that may influence acceptance of this technology. METHODS AND ANALYSIS: People living with diabetes and staff from the North East London (NEL) NHS DESP were invited to participate in two respective focus groups to codesign two online surveys exploring their perceptions and concerns around the potential introduction of AI-assisted screening.Focus group participants were representative of the local population in terms of ages and ethnicity. Participants' feedback was taken into consideration to update surveys which were circulated for further feedback. Surveys will be piloted at the NEL DESP and followed by semistructured interviews to assess accessibility, usability and to validate the surveys.Validated surveys will be distributed by other NHS DESP sites, and also via patient groups on social media, relevant charities and the British Association of Retinal Screeners. Post-survey evaluative interviews will be undertaken among those who consent to participate in further research. ETHICS AND DISSEMINATION: Ethical approval has been obtained by the NHS Research Ethics Committee (IRAS ID: 316631). Survey results will be shared and discussed with focus groups to facilitate preparation of findings for publication and to inform codesign of outreach activities to address concerns and perceptions identified.

Ethnic disparities in progression rates for sight-threatening diabetic retinopathy in diabetic eye screening: a population-based retrospective cohort study.

INTRODUCTION: The English Diabetic Eye Screening Programme (DESP) offers people living with diabetes (PLD) annual eye screening. We examined incidence and determinants of sight-threatening diabetic retinopathy (STDR) in a sociodemographically diverse multi-ethnic population. RESEARCH DESIGN AND METHODS: North East London DESP cohort data (January 2012 to December 2021) with 137 591 PLD with no retinopathy, or non-STDR at baseline in one/both eyes, were used to calculate STDR incidence rates by sociodemographic factors, diabetes type, and duration. HR from Cox models examined associations with STDR. RESULTS: There were 16 388 incident STDR cases over a median of 5.4 years (IQR 2.8-8.2; STDR rate 2.214, 95% CI 2.214 to 2.215 per 100 person-years). People with no retinopathy at baseline had a lower risk of sight-threatening diabetic retinopathy (STDR) compared with those with non-STDR in one eye (HR 3.03, 95% CI 2.91 to 3.15, p<0.001) and both eyes (HR 7.88, 95% CI 7.59 to 8.18, p<0.001). Black and South Asian individuals had higher STDR hazards than white individuals (HR 1.57, 95% CI 1.50 to 1.64 and HR 1.36, 95% CI 1.31 to 1.42, respectively). Additionally, every 5-year increase in age at inclusion was associated with an 8% reduction in STDR hazards (p<0.001). CONCLUSIONS: Ethnic disparities exist in a health system limited by capacity rather than patient economic circumstances. Diabetic retinopathy at first screen is a strong determinant of STDR development. By using basic demographic characteristics, screening programmes or clinical practices can stratify risk for sight-threatening diabetic retinopathy development.

Novel Outer Retinal Columnar Abnormalities (ORCA) and Non-Vasogenic Cystoid Macular Edema in Dense Deposit Disease.

PURPOSE: To describe the occurrence of bilateral outer retinal columnar abnormalities, non-vasogenic cystoid macular edema, and drusen in the context of dense deposit disease. METHODS: Case report. PATIENT: An 18-year-old female with dense deposit disease was referred to our specialist center for diagnosis and management with findings consistent with bilateral non-vasogenic cystoid macular edema and drusen. She was followed up in our clinic for forty months and treated with acetazolamide and ketorolac drops. RESULTS: Baseline examination revealed bilateral visual acuity (VA) reduction, and macular elevation with peripapillary drusen on fundus biomicroscopy. Optical coherence tomography revealed bilateral hyporeflective cystoid central macula changes, microcystoid changes with increased central subfield thickness (>450 microns), and outer retinal columnar abnormalities (ORCAs). Fluorescein angiography showed no evidence of macular leakage. Electrodiagnostic testing was within normal limits. Over the course of follow-up, she received treatment with acetazolamide 250mg BD PO and ketorolac 0.5% eye drops, with a partial reduction in her edema and improvement in VA. CONCLUSION: Dense deposit disease is a rare disease secondary to complement cascade dysregulation, associated with drusen. To the best of our knowledge, this is the first report of bilateral non-vasogenic cystoid macular edema and ORCA in a young female patient with dense deposit disease, confirmed with multimodal imaging.

Two-year recall for people with no diabetic retinopathy: a multi-ethnic population-based retrospective cohort study using real-world data to quantify the effect.

BACKGROUND/AIMS: The English Diabetic Eye Screening Programme (DESP) offers people living with diabetes (PLD) annual screening. Less frequent screening has been advocated among PLD without diabetic retinopathy (DR), but evidence for each ethnic group is limited. We examined the potential effect of biennial versus annual screening on the detection of sight-threatening diabetic retinopathy (STDR) and proliferative diabetic retinopathy (PDR) among PLD without DR from a large urban multi-ethnic English DESP. METHODS: PLD in North-East London DESP (January 2012 to December 2021) with no DR on two prior consecutive screening visits with up to 8 years of follow-up were examined. Annual STDR and PDR incidence rates, overall and by ethnicity, were quantified. Delays in identification of STDR and PDR events had 2-year screening intervals been used were determined. FINDINGS: Among 82 782 PLD (37% white, 36% South Asian, and 16% black people), there were 1788 incident STDR cases over mean (SD) 4.3 (2.4) years (STDR rate 0.51, 95% CI 0.47 to 0.55 per 100-person-years). STDR incidence rates per 100-person-years by ethnicity were 0.55 (95% CI 0.48 to 0.62) for South Asian, 0.34 (95% CI 0.29 to 0.40) for white, and 0.77 (95% CI 0.65 to 0.90) for black people. Biennial screening would have delayed diagnosis by 1 year for 56.3% (1007/1788) with STDR and 43.6% (45/103) with PDR. Standardised cumulative rates of delayed STDR per 100 000 persons for each ethnic group were 1904 (95% CI 1683 to 2154) for black people, 1276 (95% CI 1153 to 1412) for South Asian people, and 844 (95% CI 745 to 955) for white people. INTERPRETATION: Biennial screening would have delayed detection of some STDR and PDR by 1 year, especially among those of black ethnic origin, leading to healthcare inequalities.

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.

Divergent amino acid and sphingolipid metabolism in patients with inherited neuro-retinal disease.

OBJECTIVES: The non-essential amino acids serine, glycine, and alanine, as well as diverse sphingolipid species, are implicated in inherited neuro-retinal disorders and are metabolically linked by serine palmitoyltransferase (SPT), a key enzyme in membrane lipid biogenesis. To gain insight into the pathophysiological mechanisms linking these pathways to neuro-retinal diseases we compared patients diagnosed with two metabolically intertwined diseases: macular telangiectasia type II (MacTel), hereditary sensory autonomic neuropathy type 1 (HSAN1), or both. METHODS: We performed targeted metabolomic analyses of amino acids and broad sphingolipids in sera from a cohort of MacTel (205), HSAN1 (25) and Control (151) participants. RESULTS: MacTel patients exhibited broad alterations of amino acids, including changes in serine, glycine, alanine, glutamate, and branched-chain amino acids reminiscent of diabetes. MacTel patients had elevated 1-deoxysphingolipids but reduced levels of complex sphingolipids in circulation. A mouse model of retinopathy indicates dietary serine and glycine restriction can drive this depletion in complex sphingolipids. HSAN1 patients exhibited elevated serine, lower alanine, and a reduction in canonical ceramides and sphingomyelins compared to controls. Those patients diagnosed with both HSAN1 and MacTel showed the most significant decrease in circulating sphingomyelins. CONCLUSIONS: These results highlight metabolic distinctions between MacTel and HSAN1, emphasize the importance of membrane lipids in the progression of MacTel, and suggest distinct therapeutic approaches for these two neurodegenerative diseases.

Macular Telangiectasia Type 2: A Classification System Using MultiModal Imaging MacTel Project Report Number 10.

Purpose: To develop a severity classification for macular telangiectasia type 2 (MacTel) disease using multimodal imaging. Design: An algorithm was used on data from a prospective natural history study of MacTel for classification development. Subjects: A total of 1733 participants enrolled in an international natural history study of MacTel. Methods: The Classification and Regression Trees (CART), a predictive nonparametric algorithm used in machine learning, analyzed the features of the multimodal imaging important for the development of a classification, including reading center gradings of the following digital images: stereoscopic color and red-free fundus photographs, fluorescein angiographic images, fundus autofluorescence images, and spectral-domain (SD)-OCT images. Regression models that used least square method created a decision tree using features of the ocular images into different categories of disease severity. Main Outcome Measures: The primary target of interest for the algorithm development by CART was the change in best-corrected visual acuity (BCVA) at baseline for the right and left eyes. These analyses using the algorithm were repeated for the BCVA obtained at the last study visit of the natural history study for the right and left eyes. Results: The CART analyses demonstrated 3 important features from the multimodal imaging for the classification: OCT hyper-reflectivity, pigment, and ellipsoid zone loss. By combining these 3 features (as absent, present, noncentral involvement, and central involvement of the macula), a 7-step scale was created, ranging from excellent to poor visual acuity. At grade 0, 3 features are not present. At the most severe grade, pigment and exudative neovascularization are present. To further validate the classification, using the Generalized Estimating Equation regression models, analyses for the annual relative risk of progression over a period of 5 years for vision loss and for progression along the scale were performed. Conclusions: This analysis using the data from current imaging modalities in participants followed in the MacTel natural history study informed a classification for MacTel disease severity featuring variables from SD-OCT. This classification is designed to provide better communications to other clinicians, researchers, and patients. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Intraretinal pigmented cells in retinal degenerative disease.

PURPOSE: Invasion of pigmented cells into the retina occurs in retinal degenerative diseases, such as macular telangiectasia type 2 (MacTel) and retinitis pigmentosa (RP). These intraretinal pigmented cells may be derived from the retinal pigment epithelium (RPE), but differences and similarities between intraretinal pigmented cells and RPE have so far not been well characterised.Clinicopathologic case report. METHOD: Here, we compared intraretinal pigment cells with RPE cells by immunohistochemistry. Immunohistological stains for classic RPE markers (RPE65, CRALBP and KRT18) and blood vessel markers (lectin and collagen 4) were done on sections from postmortem eye tissue from two MacTel donors, an RP donor and a control donor. MAIN OUTCOME MEASURES: Presence of specific immunohistochemistry markers on intraretinal pigmented and RPE cells. RESULTS: We found that intraretinal pigmented cells did not express RPE65 and CRALBP, with a small subset expressing them weakly. However, they all expressed KRT18, which was also present in normal RPE cells. Interestingly, we also found clusters of KRT18-positive cells in the retina that were not pigmented. CONCLUSIONS: Our findings suggest that RPE cells invading the retina dedifferentiate (losing classic RPE markers) and can be pigmented or unpigmented. Therefore, the number of RPE cells invading the retina in retinal degenerative disease may be underappreciated by funduscopy.

Formal registration of visual impairment in people with diabetic retinopathy significantly underestimates the scale of the problem: a retrospective cohort study at a tertiary care eye hospital service in the UK.

AIMS: To analyse the prevalence of visual impairment (VI), compare it to certification of visual impairment (CVI) and analyse VI associations in patients with diabetic retinopathy (DR). METHODS: Retrospective cohort study, which included 8007 patients with DR referred from the English diabetic eye screening programme to a tertiary referral eye hospital. Main outcome measure was VI, defined as vision in the best eye of <6/24. We conducted a multivariable logistic regression for VI as primary outcome of interest, controlling for age, sex, type of diabetes, baseline DR grade, ethnicity and index of multiple deprivation (IMD). RESULTS: Mean age was 64.5 (SD 13.6) years; 61% of patients were men; and 31% of South Asian ethnicity. There were 68 patients with CVI during the study period, and 84% (272/325) of patients with VI did not have CVI after a mean follow-up of 1.87 (SD ±0.86) years. Older age showed a positive association with VI (OR per decade rise 1.88, 95% CI 1.70 to 2.08; p=1.8×10-34). Men had a lower risk of VI (OR 0.62, 95% CI 0.50 to 0.79, p=6.0×10-5), and less deprivation had a graded inverse association with VI (OR per IMD category increase 0.83, 95% CI 0.74 to 0.93, p value for linear trend 0.002). CONCLUSION: The majority of people with vision impairment are not registered at the point of care, which could translate to underestimation of diabetes-related VI and all-cause VI at a national level if replicated at other centres. Further work is needed to explore rates of VI and uptake of registration.

Training Deep Learning Models to Work on Multiple Devices by Cross-Domain Learning with No Additional Annotations.

PURPOSE: To create an unsupervised cross-domain segmentation algorithm for segmenting intraretinal fluid and retinal layers on normal and pathologic macular OCT images from different manufacturers and camera devices. DESIGN: We sought to use generative adversarial networks (GANs) to generalize a segmentation model trained on one OCT device to segment B-scans obtained from a different OCT device manufacturer in a fully unsupervised approach without labeled data from the latter manufacturer. PARTICIPANTS: A total of 732 OCT B-scans from 4 different OCT devices (Heidelberg Spectralis, Topcon 1000, Maestro2, and Zeiss Plex Elite 9000). METHODS: We developed an unsupervised GAN model, GANSeg, to segment 7 retinal layers and intraretinal fluid in Topcon 1000 OCT images (domain B) that had access only to labeled data on Heidelberg Spectralis images (domain A). GANSeg was unsupervised because it had access only to 110 Heidelberg labeled OCTs and 556 raw and unlabeled Topcon 1000 OCTs. To validate GANSeg segmentations, 3 masked graders manually segmented 60 OCTs from an external Topcon 1000 test dataset independently. To test the limits of GANSeg, graders also manually segmented 3 OCTs from Zeiss Plex Elite 9000 and Topcon Maestro2. A U-Net was trained on the same labeled Heidelberg images as baseline. The GANSeg repository with labeled annotations is at https://github.com/uw-biomedical-ml/ganseg. MAIN OUTCOME MEASURES: Dice scores comparing segmentation results from GANSeg and the U-Net model with the manual segmented images. RESULTS: Although GANSeg and U-Net achieved comparable Dice scores performance as human experts on the labeled Heidelberg test dataset, only GANSeg achieved comparable Dice scores with the best performance for the ganglion cell layer plus inner plexiform layer (90%; 95% confidence interval [CI], 68%-96%) and the worst performance for intraretinal fluid (58%; 95% CI, 18%-89%), which was statistically similar to human graders (79%; 95% CI, 43%-94%). GANSeg significantly outperformed the U-Net model. Moreover, GANSeg generalized to both Zeiss and Topcon Maestro2 swept-source OCT domains, which it had never encountered before. CONCLUSIONS: GANSeg enables the transfer of supervised deep learning algorithms across OCT devices without labeled data, thereby greatly expanding the applicability of deep learning algorithms.

A Deep Learning Framework for the Detection and Quantification of Reticular Pseudodrusen and Drusen on Optical Coherence Tomography.

Purpose: The purpose of this study was to develop and validate a deep learning (DL) framework for the detection and quantification of reticular pseudodrusen (RPD) and drusen on optical coherence tomography (OCT) scans. Methods: A DL framework was developed consisting of a classification model and an out-of-distribution (OOD) detection model for the identification of ungradable scans; a classification model to identify scans with drusen or RPD; and an image segmentation model to independently segment lesions as RPD or drusen. Data were obtained from 1284 participants in the UK Biobank (UKBB) with a self-reported diagnosis of age-related macular degeneration (AMD) and 250 UKBB controls. Drusen and RPD were manually delineated by five retina specialists. The main outcome measures were sensitivity, specificity, area under the receiver operating characteristic (ROC) curve (AUC), kappa, accuracy, intraclass correlation coefficient (ICC), and free-response receiver operating characteristic (FROC) curves. Results: The classification models performed strongly at their respective tasks (0.95, 0.93, and 0.99 AUC, respectively, for the ungradable scans classifier, the OOD model, and the drusen and RPD classification models). The mean ICC for the drusen and RPD area versus graders was 0.74 and 0.61, respectively, compared with 0.69 and 0.68 for intergrader agreement. FROC curves showed that the model's sensitivity was close to human performance. Conclusions: The models achieved high classification and segmentation performance, similar to human performance. Translational Relevance: Application of this robust framework will further our understanding of RPD as a separate entity from drusen in both research and clinical settings.

Quantification and Predictors of OCT-Based Macular Curvature and Dome-Shaped Configuration: Results From the UK Biobank.

Purpose: To investigate macular curvature, including the evaluation of potential associations and the dome-shaped macular configuration, given the increasing myopia prevalence and expected associated macular malformations. Methods: The study included a total of 65,440 subjects with a mean age (± SD) of 57.3 ± 8.11 years with spectral-domain optical coherence tomography (OCT) data from a unique contemporary resource for the study of health and disease that recruited more than half a million people in the United Kingdom (UK Biobank). A deep learning model was used to segment the retinal pigment epithelium. The macular curvature of the OCT scans was calculated by polynomial fit and evaluated. Further, associations with demographic, functional, ocular, and infancy factors were examined. Results: The overall macular curvature values followed a Gaussian distribution with high inter-eye agreement. Although all of the investigated parameters, except maternal smoking, were associated with the curvature in a multilinear analysis, ethnicity and refractive error consistently revealed the most significant effect. The prevalence of a macular dome-shaped configuration was 4.8% overall, most commonly in Chinese subjects as well as hypermetropic eyes. An increasing frequency up to 22.0% was found toward high refractive error. Subretinal fluid was rarely found in these eyes. Conclusions: Macular curvature revealed associations with demographic, functional, ocular, and infancy factors, as well as increasing prevalence of a dome-shaped macular configuration in high refractive error including high myopia and hypermetropia. These findings imply different pathophysiologic processes that lead to macular development and might open new fields to future myopia and macula research.

Foveal Curvature and Its Associations in UK Biobank Participants.

Purpose: To examine whether sociodemographic, and ocular factors relate to optical coherence tomography (OCT)-derived foveal curvature (FC) in healthy individuals. Methods: We developed a deep learning model to quantify OCT-derived FC from 63,939 participants (age range, 39-70 years). Associations of FC with sociodemographic, and ocular factors were obtained using multilevel regression analysis (to allow for right and left eyes) adjusting for age, sex, ethnicity, height (model 1), visual acuity, spherical equivalent, corneal astigmatism, center point retinal thickness (CPRT), intraocular pressure (model 2), deprivation (Townsend index), higher education, annual income, and birth order (model 3). Fovea curvature was modeled as a z-score. Results: Males had on average steeper FC (0.077; 95% confidence interval [CI] 0.077-0.078) than females (0.068; 95% CI 0.068-0.069). Compared with whites, non-white individuals showed flatter FC, particularly those of black ethnicity. In black males, -0.80 standard deviation (SD) change when compared with whites (95% CI -0.89, -0.71; P 5.2e10-68). In black females, -0.70 SD change when compared with whites (95% CI -0.77, -0.63; p 2.3e10-93). Ocular factors (visual acuity, refractive status, and CPRT) showed a graded inverse association with FC that persisted after adjustment. Macular curvature showed a positive association with FC. Income showed a linear trend increase in males (P for linear trend = 0.005). Conclusions: We demonstrate marked differences in FC with ethnicity on the largest cohort studied for this purpose to date. Ocular factors showed a graded association with FC. Implementation of FC quantification in research and on the clinical setting can enhance the understanding of clinical macular phenotypes in health and disease.