Red and green defocus curves and duochrome test in different age groups / Curvas de desenfoque rojo y verde y prueba de duocromo en diferentes grupos de edad

Purpose: To compare the eye defocus curves (DCs) obtained with stimuli on red, green, and white backgrounds and to investigate the applicability of the duochrome test (DT) in different age groups. Methods: 12 elderly (ELD: 59.3 ± 3.9 years) and 8 young (YG: 22.1 ± 1.1 years) subjects were recruited. An optometric assessment with the DT was carried out to obtain the subjective refraction at distance. DCs at distance on green, white, and red backgrounds were measured and the following parameters were deduced: dioptric difference between red-green, green-white, red-white focal positions (minima of the DCs), best corrected visual acuity (BCVA), and widths of the DCs for red, green, and white. Results: The DC difference between the green-white focal positions (mean ± standard deviation) was -0.12±0.17 diopters (D) (ELD, p = 0.012) and -0.11±0.12 D (YG, p = 0.039), while the red-white difference was not statistically significant. The DC red-green difference was 0.20±0.16 D (ELD, p = 0.002) and 0.18±0.18 D (YG, p = 0.008). The ELD BCVA with green background was significantly worse than BCVA with red (p = 0.007) and white (p = 0.007). The mean value of the DC's width in ELD for green (1.01±0.36 D) was higher than for red (0.77±0.21 D) and for white (0.84±0.35 D), but with no statistical significance. Conclusion: Both age groups showed a slight focusing preference for red when using white light. Moreover, ELD showed a worse BCVA with a green compared to a red background. Despite these results deduced by DC analyses, these aspects do not compromise the possibility of using the DT in clinical practice both in the young and in the elderly. Furthermore, the difference of about 0.20 D between red-green DC in both groups confirms the clinical appropriateness of the widespread use of 0.25 D step as the standard minimum difference in power between correcting lenses.(AU)

Investigation of factors that may affect the foveal avascular zone: An optical coherence tomography angiography study.

SIGNIFICANCE: An understanding of factors that affect the foveal avascular zone (FAZ) in healthy eyes may aid in the early identification of patients at risk of retinal pathology, thereby allowing better management and preventive measures to be implemented. PURPOSE: The size and shape of the FAZ can change due to retinal diseases associated with oxidative stress, including diabetic retinopathy, glaucoma, and macular degeneration. This study aimed to assess the relationship, if any, between factors that may affect the superficial FAZ (i.e., vessel density, vessel perfusion, overweight/obesity) and possible links with macular pigment optical density in young, healthy participants. METHODS: One hundred thirty-nine participants aged 18 to 35 years were recruited to this cross-sectional study. The superficial FAZ area, foveal vascularity, and central macular thickness (CMT) were assessed using the Cirrus 5000. Health parameters, body mass index, trunk fat %, and macular pigment were analyzed to determine possible associations with the superficial FAZ. RESULTS: Mean FAZ area was 0.23 ± 0.08 mm2. Females had a significantly larger mean FAZ area than males (p=0.002). The FAZ area was positively correlated with body mass index (Pearson's r = 0.189, p=0.026). Significant correlates of the FAZ area in the multivariate model included vessel perfusion (central), CMT, and trunk fat %, collectively explaining 65.1% of the overall variability. CONCLUSIONS: Study findings suggest that reduced vessel perfusion, thinner CMT, and higher trunk fat % are plausible predictors of a larger FAZ area in healthy Caucasian adults. Low macular pigment optical density was, however, not associated with increased FAZ size in young healthy eyes. Noninvasive optical coherence tomography angiography testing, in association with these predictors, may aid in the early detection and monitoring of retinal diseases associated with oxidative stress.

Intereye Microvascular Differences in Patients With Same-Stage Diabetic Retinopathy Revealed by OCTA.

Purpose: To evaluate microvascular intereye differences in diabetic patients with same-stage diabetic retinopathy (DR) in both eyes as assessed using optical coherence tomography angiography (OCTA). Methods: In this cross-sectional study, fovea-centered swept-source 6 × 6 mm OCTA scans were acquired using a 200 kHz OCTA device. Vessel density (VD) and fractal dimension were calculated on binarized, vessel-segmented images in the superficial capillary plexus (SCP) and deep capillary plexus (DCP). Foveal avascular zone (FAZ) area (FAZA) and perimeter (FAZP) was measured and FAZ circularity (FAZC) calculated. Absolute difference (δabs) and asymmetry index between eyes was assessed and compared across DR stages. Differences of VD, FD, and FAZ parameters between left and right eye were evaluated using linear mixed models. Results: A total of 336 eyes of 168 diabetic patients without DR and with DR stages ranging from mild nonproliferative to proliferative DR were included for analysis. The intereye comparison revealed significantly lower VD in the SCP (estimate [95% CI] = -0.009 [-0.01; -0.006], P < 0.01), as well as a significantly lower FD in the SCP (-0.007 [-0.009; -0.005], P < 0.01) of the left compared to the right eye. FAZC of the left compared to the right eye was lower in eyes without DR, moderate DR, and PDR (P < 0.05). FAZ δabs and asymmetry index were higher in more advanced disease stages (P < 0.05). Conclusions: OCTA metrics provide important information on the retinal microvasculature in systemic diseases such as DR. Our results reveal a significant intereye difference with lower VD and FD in the SCP as well as higher FAZ impairment of the left compared to the right eye.

A novel lightweight deep learning approach for simultaneous optic cup and optic disc segmentation in glaucoma detection.

Glaucoma is a chronic neurodegenerative disease that can result in irreversible vision loss if not treated in its early stages. The cup-to-disc ratio is a key criterion for glaucoma screening and diagnosis, and it is determined by dividing the area of the optic cup (OC) by that of the optic disc (OD) in fundus images. Consequently, the automatic and accurate segmentation of the OC and OD is a pivotal step in glaucoma detection. In recent years, numerous methods have resulted in great success on this task. However, most existing methods either have unsatisfactory segmentation accuracy or high time costs. In this paper, we propose a lightweight deep-learning architecture for the simultaneous segmentation of the OC and OD, where we have adopted fuzzy learning and a multi-layer perceptron to simplify the learning complexity and improve segmentation accuracy. Experimental results demonstrate the superiority of our proposed method as compared to most state-of-the-art approaches in terms of both training time and segmentation accuracy.

Imágenes multimodales y retromodo en la calcificación esclerocoroidea: reporte de un caso / Multimodal and retro-mode imaging in sclerochoroidal calcification: A case report

Presentamos un reporte de caso en una paciente de 70años sobre las calcificaciones esclerocoroideas, una rara condición que involucra depósitos de pirofosfato de calcio en el polo posterior del ojo. Proporcionamos un relato sobre la presentación clínica y su apariencia en imágenes multimodales, utilizando fotografías de color del fondo de ojo, tomografía de coherencia óptica de fuente de barrido (SS-OCT), ecografía ocular y la novedosa técnica de retromodo (RMI). Al examen la agudeza visual fue de 20/25 en el ojo derecho y de 20/20 en el ojo izquierdo. La fotografía de color del fondo de ojo reveló depósitos amarillentos localizados en la arcada temporal-superior de ambos ojos. SS-OCT demostró masas de origen escleral. Las ecografías oculares confirmaron la calcificación de estas masas. El RMI detectó imágenes hiperreflectivas con una marcada elevación superficial de las lesiones. El laboratorio sistémico no presentó alteraciones, lo que llevó al diagnóstico de calcificaciones esclerocoroideas bilaterales de origen idiopático.(AU)

We present a case report on sclerochoroidal calcification (SCC), a rare condition involving calcium pyrophosphate deposits in the posterior pole of the eye in a 70-year-old patient. We provide an account of the clinical presentation and its appearance in multimodal images, using color fundus photography, swept-source optical coherence tomography (SS-OCT), ocular ultrasound, and the novel retro-mode imaging (RMI) technique. Visual acuity was 20/25 in the right eye (OD) and 20/20 in the left eye (OS). Color fundus photography revealed yellowish deposits located in the upper temporal arcade of both eyes. SS-OCT demonstrated masses of scleral origin. Ocular ultrasounds confirmed the calcification of these masses. RMI detected hyper-reflective images with marked superficial elevation. Systemic laboratory results did not detect any abnormalities, leading to the diagnosis of bilateral idiopathic SCC.(AU)

Lipid profile alterations in non-infectious uveitis: correlation with quantitative optical coherence tomography angiography parameters.

BACKGROUND/AIMS: Lipid profiles have been changed in numerous chronic conditions. The impact of uveitis on lipid metabolism remains unclear. METHODS: This is a cross-sectional study included 416 patients with non-infectious uveitis (NIU) and 416 healthy subjects. Standard techniques were used to measure total cholesterol (TC), triglycerides (TG), high-density lipoprotein-cholesterol (HDLc), low-density lipoprotein-cholesterol (LDLc) levels. Quantitative optical coherence tomography angiography (OCTA) parameters were obtained from 500 eyes in each group. Correlation analysis examined the relationship between lipid profile and OCTA parameters. RESULTS: Patients with NIU exhibited significantly elevated TC, TG and LDLc levels compared with controls (p=0.003; p<0.001; p<0.001, respectively). Subgroup analysis revealed that HDLc was significantly lower in Behçet's disease (p=0.024) compared with controls. Vascular density (VD) in the superficial capillary plexus (SCP), deep capillary plexus (DCP), choriocapillaris and optic disk were significantly decreased in NIU eyes (p<0.05, respectively) compared with controls. HDLc exhibited a significant negative correlation with VDs in the whole and parafovea SCP (r=-0.489, p=0.008; r=-0.480, p=0.0026, respectively), while LDLc showed a significant positive correlation with VDs in the whole and parafovea DCP in NIU patients (r=0.576, p=0.032; r=0.267, p=0.034, respectively). CONCLUSIONS: The lipid profile is altered in NIU, and there are correlations between HDLc and LDLc levels and VD as measured by OCTA. Lipid profile analysis may offer valuable insights into evaluating vascular and metabolic aspects of NIU.

iGWAS: Image-based genome-wide association of self-supervised deep phenotyping of retina fundus images.

Existing imaging genetics studies have been mostly limited in scope by using imaging-derived phenotypes defined by human experts. Here, leveraging new breakthroughs in self-supervised deep representation learning, we propose a new approach, image-based genome-wide association study (iGWAS), for identifying genetic factors associated with phenotypes discovered from medical images using contrastive learning. Using retinal fundus photos, our model extracts a 128-dimensional vector representing features of the retina as phenotypes. After training the model on 40,000 images from the EyePACS dataset, we generated phenotypes from 130,329 images of 65,629 British White participants in the UK Biobank. We conducted GWAS on these phenotypes and identified 14 loci with genome-wide significance (p<5×10-8 and intersection of hits from left and right eyes). We also did GWAS on the retina color, the average color of the center region of the retinal fundus photos. The GWAS of retina colors identified 34 loci, 7 are overlapping with GWAS of raw image phenotype. Our results establish the feasibility of this new framework of genomic study based on self-supervised phenotyping of medical images.

A novel technique for extensive submacular hemorrhage using high-dose tissue plasminogen activator.

BACKGROUND: Submacular hemorrhage (SMH) is a sight-threatening disorder. Choroidal neovascularization secondary to age-related macular degeneration, polypoidal choroidal vasculopathy, trauma, angioid streaks, and pathological myopia are a few important causes. The conventional treatment of massive SMH is vitrectomy with manual removal of the clot with extensive retinectomy with/without tissue plasminogen activator (tPA). The usual dose of subretinal tPA is 10-25 µg. PURPOSE: To describe a new surgical approach in a case of massive SMH with retinal detachment without retinectomy. SYNOPSIS: In our case of near total hemorrhagic retinal detachment due to subretinal hemorrhage caused by trauma (road traffic accident), the patient presented with a visual acuity of counting fingers. Core vitrectomy was performed and posterior vitreous detachment was induced. The locations for retinotomy to inject and aspirate subretinal blood were selected at the maximum height of retinal elevation near the arcades. Recombinant tPA (10 µg/0.1 ml concentration; 0.3 ml injected in two locations) was injected subretinally with a 23-G soft tip cannula in the superotemporal and inferonasal quadrant causing subretinal bleb formation. Subsequently, the surgeon waited for approximately 20 min on the table for the liquefaction of the clot. The liquefied blood and tPA were drained with a silicone soft tip. Endolaser was performed at the retinotomy site and 1000cs silicone oil was injected. No signs of toxicity such as vitritis, vasculitis, or retinal necrosis were noted. HIGHLIGHTS: Our unique technique of high-dose intraoperative subretinal tPA (60 µg) is safe and helpful in rapid clot lysis and recovery of visual acuity. The patient gained a visual acuity of 20/80 from counting fingers after 1 month of surgery and 20/60 after silicone oil removal. A high dose of tPA aids in the immediate aspiration of blood from a small retinotomy. A 23-G soft tip was used instead of a 41-G subretinal cannula to inject a large quantity of subretinal tPA. VIDEO LINK: https://youtu.be/JzZBDUfa3NA.

Convolutional Neural Network-Based Prediction of Axial Length Using Color Fundus Photography.

Purpose: To develop convolutional neural network (CNN)-based models for predicting the axial length (AL) using color fundus photography (CFP) and explore associated clinical and structural characteristics. Methods: This study enrolled 1105 fundus images from 467 participants with ALs ranging from 19.91 to 32.59 mm, obtained at National Taiwan University Hospital between 2020 and 2021. The AL measurements obtained from a scanning laser interferometer served as the gold standard. The accuracy of prediction was compared among CNN-based models with different inputs, including CFP, age, and/or sex. Heatmaps were interpreted by integrated gradients. Results: Using age, sex, and CFP as input, the mean ± standard deviation absolute error (MAE) for AL prediction by the model was 0.771 ± 0.128 mm, outperforming models that used age and sex alone (1.263 ± 0.115 mm; P < 0.001) and CFP alone (0.831 ± 0.216 mm; P = 0.016) by 39.0% and 7.31%, respectively. The removal of relatively poor-quality CFPs resulted in a slight MAE reduction to 0.759 ± 0.120 mm without statistical significance (P = 0.24). The inclusion of age and CFP improved prediction accuracy by 5.59% (P = 0.043), while adding sex had no significant improvement (P = 0.41). The optic disc and temporal peripapillary area were highlighted as the focused areas on the heatmaps. Conclusions: Deep learning-based prediction of AL using CFP was fairly accurate and enhanced by age inclusion. The optic disc and temporal peripapillary area may contain crucial structural information for AL prediction in CFP. Translational Relevance: This study might aid AL assessments and the understanding of the morphologic characteristics of the fundus related to AL.

A fundus image dataset for intelligent retinopathy of prematurity system.

Image-based artificial intelligence (AI) systems stand as the major modality for evaluating ophthalmic conditions. However, most of the currently available AI systems are designed for experimental research using single-central datasets. Most of them fell short of application in real-world clinical settings. In this study, we collected a dataset of 1,099 fundus images in both normal and pathologic eyes from 483 premature infants for intelligent retinopathy of prematurity (ROP) system development and validation. Dataset diversity was visualized with a spatial scatter plot. Image classification was conducted by three annotators. To the best of our knowledge, this is one of the largest fundus datasets on ROP, and we believe it is conducive to the real-world application of AI systems.

Atypical acquired toxoplasmosis.

A 33-year-old male presented with unilateral painless vision loss with a history of sub-tenon steroid for the same. The fundus showed an elevated focus of retinochoroiditis with vitritis. On investigating for the cause, polymerase chain reaction test on the anterior chamber tap was found to be positive for Toxoplasma. Such confusing and atypical cases usually produce a clinical dilemma and should be managed in a stepwise manner. Ancillary investigations usually provide a clue to the clinician and should be performed without any hesitation.

Investigating the Impact of Bariatric Surgery on Macular and Peripapillary Vessel Density in Obese Individuals without Metabolic Disease.

INTRODUCTION: It is well established that microvascular structures are affected in obese people with metabolic disease. We aimed to evaluate the effect on microvascular structures by examining macular and peripapillary vessel density with optical coherence tomography angiography after bariatric surgery in obese individuals without metabolic disease. METHODS: This prospective study included 96 eyes of 48 obese patients. Body mass index (BMI), macular vessel density in the superficial, intermediate, and deep capillary plexus, and peripapillary vessel density were measured before and 6 months after bariatric surgery. RESULTS: BMI decreased significantly to 43.75 ± 4.4 kg/m2 postoperatively compared to 55.31 ± 5.1 kg/m2 preoperatively (p < 0.05). A significant increase was observed in macular vessel density in the deep capillary plexus postoperatively (p < 0.01). However, no significant postoperative increase occurred in macular vascular density in the superficial and intermediate capillary plexus (p > 0.05). Moreover, there was no change in peripapillary vascular density (p > 0.05). Postoperative thickening of the foveal, parafoveal, and perifoveal retinal layers was significant (p < 0.001). No significant correlation was detected between BMI change and macular and peripapillary vessel density changes (p > 0.05). CONCLUSION: An increase in macular vascular density, particularly in the deep capillary plexus, and retinal layer thickness has been observed following bariatric surgery performed on obese individuals without metabolic disease. This increase may indicate that microvascular structures are affected even in the absence of metabolic disease and that microperfusion improves with surgery.

A case of choroidal neovascularization as a first manifestaion of systemic lupus erythematosus.

BACKGROUND: To report a rare occurrence of pigment epitheliopathy associated with choroidal neovasculization as a first manifestation of systemic lupus erythematosus. CASE PRESENTATION: A 54-year-old female, with no prior medical history, sought a second opinion due to sudden drop in vision in her right eye to 20/80. Slit lamp examination was normal. Fundus examination revealed the presence of a subretinal hemorrhage in the macular area. Fundus imaging including optical coherence tomography and fluorescein angiography showed multifocal retinal pigment epitheliopathy associated with choroidal neovascularization (CNV). The patient had received an intravitreal injection of Bevacizumab 2 weeks ago. It was decided to complete the loading dose regimen with two additional Bevacizumab injections, and the first injection was done 2 weeks after her presentation. Two weeks later, the patient reported a rash on her cheeks, painful joints, and purpura. Systemic workup revealed positive ANA, anti-cardiolipin antibodies, and decreased complement levels, with negative anti-histone antibodies. This led to the diagnosis of systemic lupus erythematosus (SLE) based on the "Systemic Lupus International Collaborating Clinics" criteria. The patient was treated with 50 mg of prednisolone which was then tapered. 1 month after the third injection, an showed a total resolution of the sub-retinal fluid with an improvement of vision to 20/20. No recurrence was observed during follow-up. CONCLUSION: Based on the findings from the fundus exam and imaging, systemic symptoms and the blood work-up, we postulate that the pigment epitheliopathy associated with choroidal neovascularization was related to the vaso-occlusive disease at the level of the choroid that can be part of SLE vasculopathy. To our knowledge, this represents the first case in which pigment epitheliopathy and CNV were the primary manifestations of SLE.

Ixabepilone related angiographically silent macular edema.

INTRODUCTION: We present a single-eyed case with a previous diagnosis of breast cancer who had intraretinal cystoid changes associated with the systemic administration of ixabepilone in her only seeing eye. To our best knowledge, this is the first reported case describing this phenomenon related to the ixabepilone administration. CASE DESCRIPTION: A 54-year-old woman with a history of breast cancer was examined due to visual deterioration in her only good left eye. The patient had undergone cataract surgery and lens implantation in her right eye following a childhood accident, but subsequently had developed a refractory glaucoma and lost her right vision. Six cycles of 40 mg/m2 systemic ixabepilone (3-hly intravenous infusion once every 3 weeks) had been administered within the past six months. Her visual decline started two weeks following the last treatment session. She was offered intravitreal anti-vascular endothelial growth factor injection elsewhere. Fluorescein angiogram showed no dye leakage whereas spectral-domain optical coherence tomography demonstrated parafoveal intraretinal cystoid changes. En-face optical coherence tomography revealed petaloid type roundish hyporeflective areas at the level of superficial and deep vascular plexus. Ixabepilone-associated cystoid maculopathy was suspected as she received only ixabepilone for the chemotherapy in the last six months. We thus recommended her not to continue ixabepilone therapy. Ten weeks after the ixabepilone cessation, intraretinal cystoid changes had resolved completely. CONCLUSION: Angiographically silent intraretinal cystoid changes may develop in association with the use of ixabepilone. Referral to an ophthalmologist should be considered for the patients experiencing visual complaints as ixabepilone cessation may lead to visual improvement and avoid unnecessary treatment.

Comparison of 21 artificial intelligence algorithms in automated diabetic retinopathy screening using handheld fundus camera.

BACKGROUND: Diabetic retinopathy (DR) is a common complication of diabetes and may lead to irreversible visual loss. Efficient screening and improved treatment of both diabetes and DR have amended visual prognosis for DR. The number of patients with diabetes is increasing and telemedicine, mobile handheld devices and automated solutions may alleviate the burden for healthcare. We compared the performance of 21 artificial intelligence (AI) algorithms for referable DR screening in datasets taken by handheld Optomed Aurora fundus camera in a real-world setting. PATIENTS AND METHODS: Prospective study of 156 patients (312 eyes) attending DR screening and follow-up. Both papilla- and macula-centred 50° fundus images were taken from each eye. DR was graded by experienced ophthalmologists and 21 AI algorithms. RESULTS: Most eyes, 183 out of 312 (58.7%), had no DR and mild NPDR was noted in 21 (6.7%) of the eyes. Moderate NPDR was detected in 66 (21.2%) of the eyes, severe NPDR in 1 (0.3%), and PDR in 41 (13.1%) composing a group of 34.6% of eyes with referable DR. The AI algorithms achieved a mean agreement of 79.4% for referable DR, but the results varied from 49.4% to 92.3%. The mean sensitivity for referable DR was 77.5% (95% CI 69.1-85.8) and specificity 80.6% (95% CI 72.1-89.2). The rate for images ungradable by AI varied from 0% to 28.2% (mean 1.9%). Nineteen out of 21 (90.5%) AI algorithms resulted in grading for DR at least in 98% of the images. CONCLUSIONS: Fundus images captured with Optomed Aurora were suitable for DR screening. The performance of the AI algorithms varied considerably emphasizing the need for external validation of screening algorithms in real-world settings before their clinical application.

What is already known on this topic? Diabetic retinopathy (DR) is a common complication of diabetes. Efficient screening and timely treatment are important to avoid the development of sight-threatening DR. The increasing number of patients with diabetes and DR poses a challenge for healthcare.What this study adds? Telemedicine, mobile handheld devices and artificial intelligence (AI)-based automated algorithms are likely to alleviate the burden by improving efficacy of DR screening programs. Reliable algorithms of high quality exist despite the variability between the solutions.How this study might affect research, practice or policy? AI algorithms improve the efficacy of screening and might be implemented to clinical use after thorough validation in a real-life setting.

Observation of structural and vascular features of retina and choroid in myopia using ultra-widefield SS-OCTA.

BACKGROUND: To find the relationship between the changes of retinal and choriodal structure/ vascular densities (VD) and the myopia progress. METHODS: 126 eyes of 126 age-matched young participants were divided into three groups: Emmetropia and Low Myopia (EaLM) (33 eyes), Moderate Myopia (MM) (39 eyes), and High Myopia (HM) (54 eyes). Fundus images measuring 12 × 12 mm were captured using ultra-widefield swept-source optical coherence tomography angiography (SS-OCTA). Each image was uniformly divided into nine regions: supra-temporal (ST), temporal (T), infra-temporal (IT), superior (S), central macular area (C), inferior (I), supra-nasal (SN), nasal (N), and infra-nasal (IN). Various structural parameters, including inner retina thickness (IRT), outer retina thickness (ORT), and choroid thickness (CT), were assessed, and the VD of the superficial capillary plexus (SCP), deep capillary plexus (DCP), choriocapillaries (CC), and choroid vessels (ChdV) were quantified. RESULTS: CT in upper fundus exhibited a significant reduction from EaLM to MM. Additionally, ORT (ST, S. SN, C, N, IT, I, IN), CT (ST, S, SN, T, C, N, IT, I, IN) and VDs of SCP (ST, S, C, I, IN), DCP (ST, S, T, C, I) and ChdV (T, N, I, IN) were statistically diminished in EaLM compared to HM. Furthermore, IRT (N), ORT (N, IN), CT (S, SN, T, C, IT, I) and VDs of SCP (I, IN) and DCP (I) exhibited significant decreases as MM progressed towards HM. Intriguingly, there was a notable increase in the VD of CC (ST, S, T, C, N) as myopia progressed from MM to HM. CONCLUSION: Significant changes in retinal and choroid structure and vascular density occur as moderate myopia advances to high myopia. Efforts to curb myopia progression to this stage are essential, as the failure to do so may lead to the development of corresponding retinopathy.

Automated machine learning model for fundus image classification by health-care professionals with no coding experience.

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

Fundus Tessellation and Parapapillary Atrophy, as Ocular Characteristics of Spontaneously High Myopia in Macaques: The Non-Human Primates Eye Study.

Purpose: This study aimed to evaluate the ocular characteristics associated with spontaneously high myopia in adult nonhuman primates (NHPs). Methods: A total of 537 eyes of 277 macaques with an average age of 18.53 ± 3.01 years (range = 5-26 years), raised in a controlled environment, were included. We measured ocular parameters, including spherical equivalent (SE), axial length (AXL), and intraocular pressure. The 45-degree fundus images centered on the macula and the disc assessed the fundus tessellation and parapapillary atrophy (PPA). Additionally, optical coherence tomography (OCT) was used to measure the thickness of the retinal nerve fiber layer (RNFL). Results: The mean SE was -1.58 ± 3.71 diopters (D). The mean AXL was 18.76 ± 0.86 mm. The prevalence rate of high myopia was 17.7%. As myopia aggravated, the AXL increased (r = -0.498, P < 0.001). Compared with non-high myopia, highly myopic eyes had a greater AXL (P < 0.001), less RNFL thickness (P = 0.004), a higher incidence of PPA (P < 0.001), and elevated grades of fundus tessellation (P < 0.001). The binary logistic regression was performed, which showed PPA (odds ratio [OR] = 4.924, 95% confidence interval [CI] = 2.375-10.207, P < 0.001) and higher grades of fundus tessellation (OR = 1.865, 95% CI = 1.474-2.361, P < 0.001) were independent risk characteristics for high myopia. Conclusions: In NHPs, a higher grade of fundus tessellation and PPA were significant biomarkers of high myopia. Translational Relevance: The study demonstrates adult NHPs raised in conditioned rooms have a similar prevalence and highly consistent fundus changes with human beings, which strengthens the foundation for utilizing macaques as an animal model in high myopic studies.