Photographs Of Eyes Research Articles

Pupil to limbus diameter ratio as an emerging autonomic function test and its correlation with anthropometric parameters in different phases of menstrual cycle

The menstrual cycle is a physiological change in normal females, indicating the proper functioning of both endocrine and reproductive health. The pupil to limbus diameter (PLD) ratio is defined as the ratio of pupil diameter measured at an axial plane to the limbus diameter measured at the same or a parallel axial plane. Alterations in estrogen and progesterone levels may influence cardiac autonomic functions. This study aimed to correlate the PLD ratio with anthropometric parameters, such as body mass index (BMI) and waist circumference (WC), during different phases of the menstrual cycle among medical students.Methods: A cross-sectional study was conducted among first- and second-year female MBBS students aged 17 to 22 years. Anthropometric parameters, including height, weight, BMI, and WC, were measured for all participants. Eye photographs were taken during the follicular and luteal phases of the menstrual cycle, and the diameters were measured manually using the two-box method. The PLD ratios for both eyes showed a significant positive correlation with BMI (right eye: r = 0.682, p < 0.000; left eye: r = 0.430, p < 0.000) and waist circumference (right eye: r = 0.456, p < 0.000; left eye: r = 0.315, p < 0.001). The PLD ratio can serve as a simple, non-invasive, and cost-effective autonomic function test.

Comparison of veterinarians and a deep learning tool in the diagnosis of equine ophthalmic diseases.

The aim was to compare ophthalmic diagnoses made by veterinarians to a deep learning (artificial intelligence) software tool which was developed to aid in the diagnosis of equine ophthalmic diseases. As equine ophthalmology is a very specialised field in equine medicine, the tool may be able to help in diagnosing equine ophthalmic emergencies such as uveitis. In silico tool development and assessment of diagnostic performance. A deep learning tool which was developed and trained for classification of equine ophthalmic diseases was tested with 40 photographs displaying various equine ophthalmic diseases. The same data set was shown to different groups of veterinarians (equine, small animal, mixed practice, other) using an opinion poll to compare the results and evaluate the performance of the programme. Convolutional Neural Networks (CNN) were trained on 2346 photographs of equine eyes, which were augmented to 9384 images. Two hundred and sixty-one separate unmodified images were used to evaluate the trained network. The trained deep learning tool was used on 40 photographs of equine eyes (10 healthy, 12 uveitis, 18 other diseases). An opinion poll was used to evaluate the diagnostic performance of 148 veterinarians in comparison to the software tool. The probability for the correct answer was 93% for the AI programme. Equine veterinarians answered correctly in 76%, whereas other veterinarians reached 67% probability for the correct diagnosis. Diagnosis was solely based on images of equine eyes without the possibility to evaluate the inner eye. The deep learning tool proved to be at least equivalent to veterinarians in assessing ophthalmic diseases in photographs. We therefore conclude that the software tool may be useful in detecting potential emergency cases. In this context, blindness in horses may be prevented as the horse can receive accurate treatment or can be sent to an equine hospital. Furthermore, the tool gives less experienced veterinarians the opportunity to differentiate between uveitis and other ocular anterior segment disease and to support them in their decision-making regarding treatment.

Using generative AI to investigate medical imagery models and datasets

BackgroundAI models have shown promise in performing many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust of doctors in AI-based models, especially in domains where AI prediction capabilities surpass those of humans. Moreover, such explanations could enable novel scientific discovery by uncovering signals in the data that aren’t yet known to experts. MethodsIn this paper, we present a workflow for generating hypotheses to understand which visual signals in images are correlated with a classification model’s predictions for a given task. This approach leverages an automatic visual explanation algorithm followed by interdisciplinary expert review. We propose the following 4 steps: (i) Train a classifier to perform a given task to assess whether the imagery indeed contains signals relevant to the task; (ii) Train a StyleGAN-based image generator with an architecture that enables guidance by the classifier (“StylEx”); (iii) Automatically detect, extract, and visualize the top visual attributes that the classifier is sensitive towards. For visualization, we independently modify each of these attributes to generate counterfactual visualizations for a set of images (i.e. what the image would look like with the attribute increased or decreased); (iv) Formulate hypotheses for the underlying mechanisms, to stimulate future research. Specifically, present the discovered attributes and corresponding counterfactual visualizations to an interdisciplinary panel of experts so that hypotheses can account for social and structural determinants of health (e.g. whether the attributes correspond to known patho-physiological or socio-cultural phenomena, or could be novel discoveries). FindingsTo demonstrate the broad applicability of our approach, we present results on eight prediction tasks across three medical imaging modalities – retinal fundus photographs, external eye photographs, and chest radiographs. We showcase examples where many of the automatically-learned attributes clearly capture clinically known features (e.g., types of cataract, enlarged heart), and demonstrate automatically-learned confounders that arise from factors beyond physiological mechanisms (e.g., chest X-ray underexposure is correlated with the classifier predicting abnormality, and eye makeup is correlated with the classifier predicting low hemoglobin levels). We further show that our method reveals a number of physiologically plausible, previously-unknown attributes based on the literature (e.g., differences in the fundus associated with self-reported sex, which were previously unknown). InterpretationOur approach enables hypotheses generation via attribute visualizations and has the potential to enable researchers to better understand, improve their assessment, and extract new knowledge from AI-based models, as well as debug and design better datasets. Though not designed to infer causality, importantly, we highlight that attributes generated by our framework can capture phenomena beyond physiology or pathophysiology, reflecting the real world nature of healthcare delivery and socio-cultural factors, and hence interdisciplinary perspectives are critical in these investigations. Finally, we plan to release code to enable researchers to train their own StylEx models and analyze their predictive tasks of interest, and use the methodology presented in this paper for responsible interpretation of the revealed attributes. FundingGoogle

Deep Learning Identifies High-Quality Fundus Photographs and Increases Accuracy in Automated Primary Open Angle Glaucoma Detection.

To develop and evaluate a deep learning (DL) model to assess fundus photograph quality, and quantitatively measure its impact on automated POAG detection in independent study populations. Image quality ground truth was determined by manual review of 2815 fundus photographs of healthy and POAG eyes from the Diagnostic Innovations in Glaucoma Study and African Descent and Glaucoma Evaluation Study (DIGS/ADAGES), as well as 11,350 from the Ocular Hypertension Treatment Study (OHTS). Human experts assessed a photograph as high quality if of sufficient quality to determine POAG status and poor quality if not. A DL quality model was trained on photographs from DIGS/ADAGES and tested on OHTS. The effect of DL quality assessment on DL POAG detection was measured using area under the receiver operating characteristic (AUROC). The DL quality model yielded an AUROC of 0.97 for differentiating between high- and low-quality photographs; qualitative human review affirmed high model performance. Diagnostic accuracy of the DL POAG model was significantly greater (P < 0.001) in good (AUROC, 0.87; 95% CI, 0.80-0.92) compared with poor quality photographs (AUROC, 0.77; 95% CI, 0.67-0.88). The DL quality model was able to accurately assess fundus photograph quality. Using automated quality assessment to filter out low-quality photographs increased the accuracy of a DL POAG detection model. Incorporating DL quality assessment into automated review of fundus photographs can help to decrease the burden of manual review and improve accuracy for automated DL POAG detection.

A novel technique for CAD-CAM assisted digital ocular prosthesis.

There are various techniques available for constructing a custom ocular prosthesis. The present technique report describes a digital workflow for constructing an ocular prosthesis using computed tomography integrated with digital technologies. The outer region of the healthy eyeball was segmented to produce the top surface of the prosthesis, while the contour and bottom surface were segmented from the tissue bed of the anophthalmic socket. The iris position was determined by tracing the optical nerve and confirmed by superimposing the patient's facial scan onto the soft tissue model of the computed tomography. Using these parameters, a standard tessellation language file for the ocular prosthesis was generated and 3D printed. The iris was then printed via UV technology using digital photographs of the patient's contralateral eye; characterization of the sclera and the final layer of clear acrylic resin were done conventionally.

Tear inflammatory cytokines as potential biomarkers for myopic macular degeneration

Previous studies have reported that inflammatory cytokine levels increase in the intraocular fluids (aqueous humor and vitreous) of highly myopic eyes, However, there has been currently no study revealing the levels of inflammatory cytokines in tear. Therefore, this study aimed to determine tear cytokine levels of highly myopic eyes, and their relationships with myopic macular degeneration (MMD).This case-control study screened inflammatory cytokines of tear samples from 132 highly myopic and 105 emmetropic eyes using a multiplex cytokine antibody array, and cytokines showing significant intergroup differences were further validated using ProQuantum immunoassays in tear samples from another 60 highly myopic and 60 emmetropic eyes. Ultra-widefield fundus photographs of eyes were classified according to the meta-analyses of the Pathologic Myopia Classification. Associations between tear cytokine levels and MMD category were investigated.As a result, tear levels of interleukin (IL)-6, IL-13 and monocyte chemoattractant protein (MCP)-1 were screened significantly higher in highly myopic eyes than in emmetropic controls (IL-6: 11.70 ± 16.81 versus 8.22 ± 10.76 pg/mL; MCP-1: 63.60 ± 54.40 versus 33.87 ± 43.82 pg/mL; both P < 0.05). Validation assays further demonstrated the elevated concentrations of IL-6 and MCP-1 (IL-6: 13.97 ± 8.41 versus 8.06 ± 7.94 pg/mL, P < 0.001; MCP-1: 32.69 ± 8.41 versus 18.07 ± 8.41 pg/mL, P = 0.003). Tear levels of IL-6 and MCP-1 differed significantly among MMD categories (both P < 0.05). The area under receiver operating characteristic curve were 0.783 and 0.682 respectively (both P < 0.05), when using tear IL-6 and MCP-1 levels to predict the presence of MMD (category ≥2). The ordered logistic regression model also indicated that longer axial length, and higher IL-6 and MCP-1 tear levels were independent predictors of higher MMD category. In our study, highly myopic eyes presented significantly higher levels of tear IL-6 and MCP-1, which may also serve as potential biomarkers for MMD.

Accuracy of Artificial Intelligence in Estimating Best-Corrected Visual Acuity From Fundus Photographs in Eyes With Diabetic Macular Edema

Best-corrected visual acuity (BCVA) is a measure used to manage diabetic macular edema (DME), sometimes suggesting development of DME or consideration of initiating, repeating, withholding, or resuming treatment with anti-vascular endothelial growth factor. Using artificial intelligence (AI) to estimate BCVA from fundus images could help clinicians manage DME by reducing the personnel needed for refraction, the time presently required for assessing BCVA, or even the number of office visits if imaged remotely. To evaluate the potential application of AI techniques for estimating BCVA from fundus photographs with and without ancillary information. Deidentified color fundus images taken after dilation were used post hoc to train AI systems to perform regression from image to BCVA and to evaluate resultant estimation errors. Participants were patients enrolled in the VISTA randomized clinical trial through 148 weeks wherein the study eye was treated with aflibercept or laser. The data from study participants included macular images, clinical information, and BCVA scores by trained examiners following protocol refraction and VA measurement on Early Treatment Diabetic Retinopathy Study (ETDRS) charts. Primary outcome was regression evaluated by mean absolute error (MAE); the secondary outcome included percentage of predictions within 10 letters, computed over the entire cohort as well as over subsets categorized by baseline BCVA, determined from baseline through the 148-week visit. Analysis included 7185 macular color fundus images of the study and fellow eyes from 459 participants. Overall, the mean (SD) age was 62.2 (9.8) years, and 250 (54.5%) were male. The baseline BCVA score for the study eyes ranged from 73 to 24 letters (approximate Snellen equivalent 20/40 to 20/320). Using ResNet50 architecture, the MAE for the testing set (n = 641 images) was 9.66 (95% CI, 9.05-10.28); 33% of the values (95% CI, 30%-37%) were within 0 to 5 letters and 28% (95% CI, 25%-32%) within 6 to 10 letters. For BCVA of 100 letters or less but more than 80 letters (20/10 to 20/25, n = 161) and 80 letters or less but more than 55 letters (20/32 to 20/80, n = 309), the MAE was 8.84 letters (95% CI, 7.88-9.81) and 7.91 letters (95% CI, 7.28-8.53), respectively. This investigation suggests AI can estimate BCVA directly from fundus photographs in patients with DME, without refraction or subjective visual acuity measurements, often within 1 to 2 lines on an ETDRS chart, supporting this AI concept if additional improvements in estimates can be achieved.

Comparison of posterior vitreous detachment-related and glaucomatous optic disc hemorrhage

This study compared the characteristics of posterior vitreous detachment (PVD)-related and glaucomatous optic disc hemorrhage (DH). Fundus photographs of eyes with PVD-related DH (PVD group) and glaucomatous DH (glaucoma group) were reviewed. The shape, type, layer, location (clock-hour sector), and DH/disc area (DH/DA) ratio of DH were investigated. In the PVD group, DH presented as a flame (60.9%), splinter (34.8%), and dot or blot (4.3%) shape. However, most of the glaucomatous DH revealed a splinter shape (92.3%), followed by a flame shape (7.7%, p < 0.001). In the PVD group, the most common type of DH was cup margin type (52.2%), whereas, in the glaucoma group it was disc rim type (53.8%, p = 0.003). Both PVD-related and glaucomatous DH were most commonly observed in the 7 o’clock sector. In the PVD group, DH was also found in the 2 and 5 o’clock sectors (p = 0.010). Mean DH/DA ratio in PVD group (0.15 ± 0.19) was greater than in glaucoma group (0.04 ± 0.04, p < 0.001). PVD-related DH showed a higher frequency of flame shape, cup margin type, nasal location, and greater area compared to the glaucomatous DH.

A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study

Photographs of the external eye were recently shown to reveal signs of diabetic retinal disease and elevated glycated haemoglobin. This study aimed to test the hypothesis that external eye photographs contain information about additional systemic medical conditions. We developed a deep learning system (DLS) that takes external eye photographs as input and predicts systemic parameters, such as those related to the liver (albumin, aspartate aminotransferase [AST]); kidney (estimated glomerular filtration rate [eGFR], urine albumin-to-creatinine ratio [ACR]); bone or mineral (calcium); thyroid (thyroid stimulating hormone); and blood (haemoglobin, white blood cells [WBC], platelets). This DLS was trained using 123 130 images from 38 398 patients with diabetes undergoing diabetic eye screening in 11 sites across Los Angeles county, CA, USA. Evaluation focused on nine prespecified systemic parameters and leveraged three validation sets (A, B, C) spanning 25 510 patients with and without diabetes undergoing eye screening in three independent sites in Los Angeles county, CA, and the greater Atlanta area, GA, USA. We compared performance against baseline models incorporating available clinicodemographic variables (eg, age, sex, race and ethnicity, years with diabetes). Relative to the baseline, the DLS achieved statistically significant superior performance at detecting AST >36·0 U/L, calcium <8·6 mg/dL, eGFR <60·0 mL/min/1·73 m2, haemoglobin <11·0 g/dL, platelets <150·0 × 103/μL, ACR ≥300 mg/g, and WBC <4·0 × 103/μL on validation set A (a population resembling the development datasets), with the area under the receiver operating characteristic curve (AUC) of the DLS exceeding that of the baseline by 5·3-19·9% (absolute differences in AUC). On validation sets B and C, with substantial patient population differences compared with the development datasets, the DLS outperformed the baseline for ACR ≥300·0 mg/g and haemoglobin <11·0 g/dL by 7·3-13·2%. We found further evidence that external eye photographs contain biomarkers spanning multiple organ systems. Such biomarkers could enable accessible and non-invasive screening of disease. Further work is needed to understand the translational implications. Google.

Diabetes and heart disease identification using biomedical iris data

The World Health Organization (WHO) report shows that Heart disease is the major cause of death all over the world i.e. nearly 21.2 million people die every year directly or indirectly from Cardiovascular (Heart) diseases estimated 32% of all deaths worldwide. Whereas, Diabetes is at the ninth position for the death all over the world i.e. nearly 3.7 million people die every year from diabetes estimated 6.61% of all deaths worldwide. The Heart and Pancreas organ play a most important role in human being. The blood flows in all parts of the body through heart. The function of pancreas is to regulate maintain the insulin levels that is responsible for diabetes. The detection of heart disease and diabetes takes too much time and very costly process. In our research, we develop a Heart Disease and Diabetes Identification System based on Iris Healthcare Kiosk. We proposed a desktop system application that detects these diseases through the Iris. The process starts by taking the left Eye photograph of the patient's through Eyeronec (company name) camera and perform intermediates operations of target cropping, pre-processing, auto-cropping (through integral projection and removing sclera), heart regions of interest (ROI) measuring, pancreatic measuring, extracting the feature and finally classify in the result. The classification result shows that 83% tests are successful, 11% tests are scant whereas 6% tests became fail. The operation is performed on 32 different training digital data sets and final result is labelled as normal or abnormal. The result shows that accuracy of our proposed system in heart disease and diabetes are 86.36% and 90.91% respectively.

The non-human animal reading the mind in the eyes test (NARMET): A new measure for the assessment of social cognition.

The Reading the Mind in the Eyes test (RMET) is a widely applied test of social cognition, based on mental state judgments in response to photographs of human eyes, which can elicit impairment in patients with numerous psychiatric and neurological disorders. However, interpretation of task performance is limited without the use of appropriate control tasks. In addition to a matched task requiring age judgments of the RMET stimuli, it was recently shown that a mental state judgment task of comparable difficulty, could be developed using photographs of domestic cat eyes. The current study aimed to further develop a Non-human Animal RMET (NARMET) by testing additional stimuli in the form of photographs of domestic dog eyes. A variety of additional tasks were used alongside the eyes test stimuli in a large sample of healthy young adults, to explore how alexithymia, schizotypal features, and autistic tendencies may differentially influence mental state attribution in response to cat, dog, and human eyes test stimuli. The resulting NARMET features both cat and dog trials, depicting a similar range of complex mental states to the human RMET. It shows favorable psychometric properties as well as being well matched to the RMET in terms of linguistic variables, length and difficulty. However, reading measures predicted performance on the RMET, but not on the NARMET. Although further testing is required in samples with a higher proportion of males, future application of the NARMET in neuropsychiatric populations exhibiting cognitive and behavioral difficulties could offer enhanced assessment of social cognitive skills.

Frequent experience with face coverings for 10 months improves emotion perception among individuals with high autistic traits: A repeated cross-sectional study.

Face coverings pose difficulties for emotion recognition, but it is unclear whether improvement in recognising emotions from the eyes is possible with experience and whether this might be dependent on one's autistic traits, given the associations between high autistic traits and poorer emotion perception and reduced gaze to the eye region. In this preregistered study, participants completed a forced-choice emotion recognition task with photographs of eyes and demographic questionnaires that measure their autistic traits and their interaction frequency with others wearing face coverings at two time points: once at the start of the face covering mandate and again 10 months later. We found that after 10 months, individuals with high autistic traits as a cohort recognised emotions from just the eyes better as a function of their experience with others wearing face coverings, suggesting that emotion perception is malleable even for those who have difficulties with emotion perception.

Glaucoma progression in patients receiving intravitreal anti-VEGF treatment for neovascular age-related macular degeneration.

The purpose of this study was to investigate how often glaucoma and neovascular age-related macular degeneration (nAMD) occur in the same patient and to evaluate whether glaucoma progression is faster in eyes treated with intravitreal anti-VEGF medications for nAMD. This single-centre retrospective real-world data (RWD) consists of medical records of 6314 glaucoma and 2166 nAMD patients treated in 2008-2017 in Tays Eye Centre, Finland. To study glaucoma progression, changes in visual fields (mean deviation [MD], dB/year), IOP (mmHg/year) and fundus photographs (progression, yes/no) were compared in glaucoma eyes with and without anti-VEGF treatment for nAMD and ≥1year follow-up. During the 10-year period, 147 patients with glaucoma received intravitreal anti-VEGF treatment for nAMD corresponding to 2% of glaucoma and 7% of nAMD patients. The mean change in MD was -0.70 dB/year (SD 1.8) vs. -0.27 dB/year (SD 1.7) (p= 0.027) in glaucoma eyes with (n= 37) and without (n= 4304) anti-VEGF injections, respectively. In patients with bilateral glaucoma and unilateral nAMD treated with anti-VEGF injections (n= 20), MD declined at -0.62 dB/year (SD 1.9) vs 0.33 dB/year (SD 1.5) (p= 0.654), and glaucoma progression was detected in 14/20 vs 10/20 (p= 0.219) fundus photographs in eyes with anti-VEGF treatment compared with their untreated fellow eyes. nAMD and glaucoma were found co-existing in the same eye at rates that were similar to the age-corrected prevalence of the two diseases in the general population. Our results suggest that intravitreal anti-VEGF treatment for nAMD may accelerate glaucoma progression.

Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization

To compare the diagnostic accuracy and explainability of a Vision Transformer deep learning technique, Data-efficient image Transformer (DeiT), and ResNet-50, trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG) and identify the salient areas of the photographs most important for each model's decision-making process. Evaluation of a diagnostic technology. Overall 66 715 photographs from 1636 OHTS participants and an additional 5 external datasets of 16 137 photographs of healthy and glaucoma eyes. Data-efficient image Transformer models were trained to detect 5 ground-truth OHTS POAG classifications: OHTS end point committee POAG determinations because of disc changes (model 1), visual field (VF) changes (model 2), or either disc or VF changes (model 3) and Reading Center determinations based on disc (model 4) and VFs (model 5). The best-performing DeiT models were compared with ResNet-50 models on OHTS and 5 external datasets. Diagnostic performance was compared using areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities. The explainability of the DeiT and ResNet-50 models was compared by evaluating the attention maps derived directly from DeiT to 3 gradient-weighted class activation map strategies. Compared with our best-performing ResNet-50 models, the DeiT models demonstrated similar performance on the OHTS test sets for all 5 ground-truth POAG labels; AUROC ranged from 0.82 (model 5) to 0.91 (model 1). Data-efficientimage Transformer AUROC was consistently higher than ResNet-50 on the 5 external datasets. For example, AUROC for the main OHTS end point (model 3) was between 0.08 and 0.20 higher in the DeiT than ResNet-50 models. The saliency maps from the DeiT highlight localized areas of the neuroretinal rim, suggesting important rim features for classification. The same maps in the ResNet-50 models show a more diffuse, generalized distribution around the optic disc. Vision Transformers have the potential to improve generalizability and explainability in deep learning models, detecting eye disease and possibly other medical conditions that rely on imaging for clinical diagnosis and management.

The Asian Eye: Anthropometric Eye Measurements of Attractiveness in Young East Asian Women.

Because of the high volume of Asian eyelid operations performed and the complexity of the Asian eye, there is a need to define exactly what anthropometric measurements determine attractiveness. Eye photographs of young East Asian women were collected from publicly available sources online. Photographs were evaluated on a Likert scale ranging from 1 to 5 for attractiveness. Thirty-seven anthropometric measurements were collected using ImageJ from the most attractive and least attractive eyes to discover which features play the most important role in attractiveness. A total of 322 right eye photographs were evaluated for attractiveness. Sixty-six eyes received a median score of greater than or equal to 4.0 and were included in the attractive cohort. Forty-three eyes received a score of less than or equal to 2.0 and were included in the unattractive cohort. The superior brow peak was more lateralized compared to the upper lid crease and upper lash line peaks in attractive eyes. A greater palpebral aperture height-to-upper lid show ratio was found to be more associated with attractive eyes than with unattractive eyes. At the midpupillary line, the ratio was on average 1.58 ± 0.32 in attractive eyes and 1.22 ± 0.43 in unattractive eyes ( p < 0.001). Eyes with convergence of the upper lid crease with the upper lash line were more likely to be deemed unattractive ( p < 0.001). East Asian eyes have specific anthropometric measurements that are more associated with attractiveness. These ideal measurements are different from those in Caucasians, suggesting ethnic variability in features defining attractiveness and a need to tailor surgical care appropriately.

Determining vertical fusion values from digital photographs of healthy eyes.

To determine the mean difference of vertical corneal light reflex (VCLR) among healthy eyes via digital photography. Retrospective study. The study enrolled 155, healthy eyes participants, 71 males and 84 females with a mean age of 14.7years (range 12-19years). The participants received complete eye examinations and 2 digital photographs were taken, with the flash on, while participants fixated their eyes on a near and a distant target. Two hundred and eighty qualified photographs were analyzed by Photo-Hirschberg testing using computer software. The vertical corneal light reflex ratio (VCLRR) was calculated as the distance of the corneal light reflex (CLR) to the inferior limbus or to the pupillary border divided by the horizontal corneal diameter, defined as VCLRR1 or VCLRR2. VCLRR was analyzed using Spearman's correlation. The mean ± SD of horizontal corneal diameter in near and distance photographs was 11.47 ± 0.62 and 11.37 ± 0.58mm, respectively. For correlation analysis, at 1m fixation and 6m fixation, the number of participants within an acceptable range of vertical fusion were 94.6% and 100% of participants. The 95th percentiles (estimated as the mean ± 1.64SD) in VCLRR1 between the two eyes at near and at distance fixation were 0.0316 and 0.0272, respectively; whereas the corresponding values for VCLRR2 were 0.0309 and 0.0240, respectively. The normal range of the vertical corneal light reflex ratio suggests that the Photo-Hirschberg test could be used for screening vertical strabismus cases depending on iris pigment.

Posterior Capsular Outcomes of Pediatric Cataract Surgery With In-The-Bag Intraocular Lens Implantation.

AimTo investigate the change of posterior capsular outcomes of pediatric cataract surgery with primary in-the-bag intraocular lens (IOL) implantation.MethodsWe conducted a case series of pediatric cataract children who underwent cataract extraction with primary in-the-bag IOL implantation, posterior capsulorhexis or vitrectorhexis, and limited anterior vitrectomy at the Eye Hospital of Wenzhou Medical University between 2016 and 2019. Digital retro-illumination photographs of pediatric eyes were obtained at baseline and 6 months, 12 months, and the last visit postoperatively. Capsular outcomes of the posterior capsular opening area (PCOA) and lens reprolifration area at those time points were compared. Correlations between the PCOA and influential factors, such as age at surgery, axial growth, and follow-up duration, were analyzed. The study was registered at register.clinicaltrials.gov (NCT04803097).ResultsData of 23 patients (27 eyes) were used in the final analysis. During follow-up, the PCOA enlarged at a rate of 0.29–0.32 mm2/month during the first six months postoperatively and 0.05–0.08 mm2/month over the next 1–2 years. Six months postoperatively, the PCOA enlargement statistically and positively correlated with the follow-up duration and axial growth. The area of lens reprolifration was 0.46 ± 1.00 mm2 at six months postoperatively and then remained stable.ConclusionThe PCOA enlarged rapidly within the first six months after the pediatric cataract surgery with primary IOL implantation. Six months postoperatively, the enlargement of PCOA was positively correlated with follow-up duration and axial growth. Posterior capsulorhexis or capsulectomy should be performed with a diameter of 3.0 to 4.0 mm for good visual axis transparency and the protection of in-the-bag IOL.

Detection of signs of disease in external photographs of the eyes via deep learning.

Retinal fundus photographs can be used to detect a range of retinal conditions. Here we show that deep-learning models trained instead on external photographs of the eyes can be used to detect diabetic retinopathy (DR), diabetic macular oedema and poor blood glucose control. We developed the models using eye photographs from 145,832 patients with diabetes from 301 DR screening sites and evaluated the models on four tasks and four validation datasets with a total of 48,644 patients from 198 additional screening sites. For all four tasks, the predictive performance of the deep-learning models was significantly higher than the performance of logistic regression models using self-reported demographic and medical history data, and the predictions generalized to patients with dilated pupils, to patients from a different DR screening programme and to a general eye care programme that included diabetics and non-diabetics. We also explored the use of the deep-learning models for the detection of elevated lipid levels. The utility of external eye photographs for the diagnosis and management of diseases should be further validated with images from different cameras and patient populations.

Detecting Glaucoma in the Ocular Hypertension Study Using Deep Learning

Automated deep learning (DL) analyses of fundus photographs potentially can reduce the cost and improve the efficiency of reading center assessment of end points in clinical trials. To investigate the diagnostic accuracy of DL algorithms trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS) to detect primary open-angle glaucoma (POAG). In this diagnostic study, 1636 OHTS participants from 22 sites with a mean (range) follow-up of 10.7 (0-14.3) years. A total of 66 715 photographs from 3272 eyes were used to train and test a ResNet-50 model to detect the OHTS Endpoint Committee POAG determination based on optic disc (287 eyes, 3502 photographs) and/or visual field (198 eyes, 2300 visual fields) changes. Three independent test sets were used to evaluate the generalizability of the model. Areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities were calculated to compare model performance. Evaluation of false-positive rates was used to determine whether the DL model detected POAG before the OHTS Endpoint Committee POAG determination. A total of 1147 participants were included in the training set (661 [57.6%] female; mean age, 57.2 years; 95% CI, 56.6-57.8), 167 in the validation set (97 [58.1%] female; mean age, 57.1 years; 95% CI, 55.6-58.7), and 322 in the test set (173 [53.7%] female; mean age, 57.2 years; 95% CI, 56.1-58.2). The DL model achieved an AUROC of 0.88 (95% CI, 0.82-0.92) for the OHTS Endpoint Committee determination of optic disc or VF changes. For the OHTS end points based on optic disc changes or visual field changes, AUROCs were 0.91 (95% CI, 0.88-0.94) and 0.86 (95% CI, 0.76-0.93), respectively. False-positive rates (at 90% specificity) were higher in photographs of eyes that later developed POAG by disc or visual field (27.5% [56 of 204]) compared with eyes that did not develop POAG (11.4% [50 of 440]) during follow-up. The diagnostic accuracy of the DL model developed on the optic disc end point applied to 3 independent data sets was lower, with AUROCs ranging from 0.74 (95% CI, 0.70-0.77) to 0.79 (95% CI, 0.78-0.81). The model's high diagnostic accuracy using OHTS photographs suggests that DL has the potential to standardize and automate POAG determination for clinical trials and management. In addition, the higher false-positive rate in early photographs of eyes that later developed POAG suggests that DL models detected POAG in some eyes earlier than the OHTS Endpoint Committee, reflecting the OHTS design that emphasized a high specificity for POAG determination by requiring a clinically significant change from baseline.

A Novel Deep Learning-Based Black Fungus Disease Identification Using Modified Hybrid Learning Methodology.

Currently, countries across the world are suffering from a prominent viral infection called COVID-19. Most countries are still facing several issues due to this disease, which has resulted in several fatalities. The first COVID-19 wave caused devastation across the world owing to its virulence and led to a massive loss in human lives, impacting the country's economy drastically. A dangerous disease called mucormycosis was discovered worldwide during the second COVID-19 wave, in 2021, which lasted from April to July. The mucormycosis disease is commonly known as “black fungus,” which belongs to the fungus family Mucorales. It is usually a rare disease, but the level of destruction caused by the disease is vast and unpredictable. This disease mainly targets people already suffering from other diseases and consuming heavy medication to counter the disease they are suffering from. This is because of the reduction in antibodies in the affected people. Therefore, the patient's body does not have the ability to act against fungus-oriented infections. This black fungus is more commonly identified in patients with coronavirus disease in certain country. The condition frequently manifests on skin, but it can also harm organs such as eyes and brain. This study intends to design a modified neural network logic for an artificial intelligence (AI) strategy with learning principles, called a hybrid learning-based neural network classifier (HLNNC). The proposed method is based on well-known techniques such as convolutional neural network (CNN) and support vector machine (SVM). This article discusses a dataset containing several eye photographs of patients with and without black fungus infection. These images were collected from the real-time records of people afflicted with COVID followed by the black fungus. This proposed HLNNC scheme identifies the black fungus disease based on the following image processing procedures: image acquisition, preprocessing, feature extraction, and classification; these procedures were performed considering the dataset training and testing principles with proper performance analysis. The results of the procedure are provided in a graphical format with the precise specification, and the efficacy of the proposed method is established.