Locality is the strongest predictor of expert performance in image-based differentiation of bacterial and fungal corneal ulcers from India.

PURPOSE: This study sought to identify the sources of differential performance and misclassification error among local (Indian) and external (non-Indian) corneal specialists in identifying bacterial and fungal keratitis based on corneal photography. METHODS: This study is a secondary analysis of survey data assessing the ability of corneal specialists to identify acute bacterial versus fungal keratitis by using corneal photography. One-hundred images of 100 eyes from 100 patients with acute bacterial or fungal keratitis in South India were previously presented to an international cohort of cornea specialists for interpretation over the span of April to July 2021. Each expert provided a predicted probability that the ulcer was either bacterial or fungal. Using these data, we performed multivariable linear regression to identify factors predictive of expert performance, accounting for primary practice location and surrogate measures to infer local fungal ulcer prevalence, including locality, latitude, and dew point. In addition, Brier score decomposition was used to determine experts' reliability ("calibration") and resolution ("boldness") and were compared between local (Indian) and external (non-Indian) experts. RESULTS: Sixty-six experts from 16 countries participated. Indian practice location was the only independently significant predictor of performance in multivariable linear regression. Resolution among Indian experts was significantly better (0.08) than among non-Indian experts (0.01; P < 0.001), indicating greater confidence in their predictions. There was no significant difference in reliability between the two groups ( P = 0.40). CONCLUSION: Local cornea experts outperformed their international counterparts independent of regional variability in tropical risk factors for fungal keratitis. This may be explained by regional characteristics of infectious ulcers with which local corneal specialists are familiar.

Implementation of optical coherence tomography in retinopathy of prematurity screening.

PURPOSE OF REVIEW: In this review, we explore the investigational applications of optical coherence tomography (OCT) in retinopathy of prematurity (ROP), the insights they have delivered thus far, and key milestones for its integration into the standard of care. RECENT FINDINGS: While OCT has been widely integrated into clinical management of common retinal diseases, its use in pediatric contexts has been undermined by limitations in ergonomics, image acquisition time, and field of view. Recently, investigational handheld OCT devices have been reported with advancements including ultra-widefield view, noncontact use, and high-speed image capture permitting real-time en face visualization. These developments are compelling for OCT as a more objective alternative with reduced neonatal stress compared to indirect ophthalmoscopy and/or fundus photography as a means of classifying and monitoring ROP. SUMMARY: OCT may become a viable modality in management of ROP. Ongoing innovation surrounding handheld devices should aim to optimize patient comfort and image resolution in the retinal periphery. Future clinical investigations may seek to objectively characterize features of peripheral stage and explore novel biomarkers of disease activity.

Improving the repeatability of deep learning models with Monte Carlo dropout.

The integration of artificial intelligence into clinical workflows requires reliable and robust models. Repeatability is a key attribute of model robustness. Ideal repeatable models output predictions without variation during independent tests carried out under similar conditions. However, slight variations, though not ideal, may be unavoidable and acceptable in practice. During model development and evaluation, much attention is given to classification performance while model repeatability is rarely assessed, leading to the development of models that are unusable in clinical practice. In this work, we evaluate the repeatability of four model types (binary classification, multi-class classification, ordinal classification, and regression) on images that were acquired from the same patient during the same visit. We study the each model's performance on four medical image classification tasks from public and private datasets: knee osteoarthritis, cervical cancer screening, breast density estimation, and retinopathy of prematurity. Repeatability is measured and compared on ResNet and DenseNet architectures. Moreover, we assess the impact of sampling Monte Carlo dropout predictions at test time on classification performance and repeatability. Leveraging Monte Carlo predictions significantly increases repeatability, in particular at the class boundaries, for all tasks on the binary, multi-class, and ordinal models leading to an average reduction of the 95% limits of agreement by 16% points and of the class disagreement rate by 7% points. The classification accuracy improves in most settings along with the repeatability. Our results suggest that beyond about 20 Monte Carlo iterations, there is no further gain in repeatability. In addition to the higher test-retest agreement, Monte Carlo predictions are better calibrated which leads to output probabilities reflecting more accurately the true likelihood of being correctly classified.

Health Equity and Disparities in ROP Care: A Need for Systematic Evaluation.

Retinopathy of prematurity (ROP) is a vasoproliferative retinal disorder that can have devastating visual sequelae if not managed appropriately. From an ophthalmology standpoint, ROP care is complex, since it spans multiple care settings and providers, including those in the neonatal intensive care unit (NICU), step down nurseries, and the outpatient clinic setting. This requires coordination and communication between providers, ancillary staff, and most importantly, effective communication with the patient's family members and caregivers. Often, factors related to the social determinants of health play a significant role in effective communication and care coordination with the family, and it is important for ophthalmologists to recognize these risk factors. The aim of this article is to (1) review the literature related to disparities in preterm birth outcomes and infants at risk for ROP; (2) identify barriers to ROP care and appropriate follow up, and (3) describe patient-oriented solutions and future directions for improving ROP care through a health equity lens.

Federated Learning for Multicenter Collaboration in Ophthalmology: Implications for Clinical Diagnosis and Disease Epidemiology.

OBJECTIVE: To utilize a deep learning (DL) model trained via federated learning (FL), a method of collaborative training without sharing patient data, to delineate institutional differences in clinician diagnostic paradigms and disease epidemiology in retinopathy of prematurity (ROP). DESIGN: Evaluation of a diagnostic test or technology. SUBJECTS AND CONTROLS: We included 5245 patients with wide-angle retinal imaging from the neonatal intensive care units of 7 institutions as part of the Imaging and Informatics in ROP study. Images were labeled with the clinical diagnoses of plus disease (plus, preplus, no plus), which were documented in the chart, and a reference standard diagnosis was determined by 3 image-based ROP graders and the clinical diagnosis. METHODS: Demographics (birth weight, gestational age) and clinical diagnoses for all eye examinations were recorded from each institution. Using an FL approach, a DL model for plus disease classification was trained using only the clinical labels. The 3 class probabilities were then converted into a vascular severity score (VSS) for each eye examination, as well as an "institutional VSS," in which the average of the VSS values assigned to patients' higher severity ("worse") eyes at each examination was calculated for each institution. MAIN OUTCOME MEASURES: We compared demographics, clinical diagnoses of plus disease, and institutional VSSs between institutions using the McNemar-Bowker test, 2-proportion Z test, and 1-way analysis of variance with post hoc analysis by the Tukey-Kramer test. Single regression analysis was performed to explore the relationship between demographics and VSSs. RESULTS: We found that the proportion of patients diagnosed with preplus disease varied significantly between institutions (P < 0.001). Using the DL-derived VSS trained on the data from all institutions using FL, we observed differences in the institutional VSS and the level of vascular severity diagnosed as no plus (P < 0.001) across institutions. A significant, inverse relationship between the institutional VSS and mean gestational age was found (P = 0.049, adjusted R2 = 0.49). CONCLUSIONS: A DL-derived ROP VSS developed without sharing data between institutions using FL identified differences in the clinical diagnoses of plus disease and overall levels of ROP severity between institutions. Federated learning may represent a method to standardize clinical diagnoses and provide objective measurements of disease for image-based diseases.

Federated Learning for Multicenter Collaboration in Ophthalmology: Improving Classification Performance in Retinopathy of Prematurity.

OBJECTIVE: To compare the performance of deep learning classifiers for the diagnosis of plus disease in retinopathy of prematurity (ROP) trained using 2 methods for developing models on multi-institutional data sets: centralizing data versus federated learning (FL) in which no data leave each institution. DESIGN: Evaluation of a diagnostic test or technology. SUBJECTS: Deep learning models were trained, validated, and tested on 5255 wide-angle retinal images in the neonatal intensive care units of 7 institutions as part of the Imaging and Informatics in ROP study. All images were labeled for the presence of plus, preplus, or no plus disease with a clinical label and a reference standard diagnosis (RSD) determined by 3 image-based ROP graders and the clinical diagnosis. METHODS: We compared the area under the receiver operating characteristic curve (AUROC) for models developed on multi-institutional data, using a central approach initially, followed by FL, and compared locally trained models with both approaches. We compared the model performance (κ) with the label agreement (between clinical and RSD), data set size, and number of plus disease cases in each training cohort using the Spearman correlation coefficient (CC). MAIN OUTCOME MEASURES: Model performance using AUROC and linearly weighted κ. RESULTS: Four settings of experiment were used: FL trained on RSD against central trained on RSD, FL trained on clinical labels against central trained on clinical labels, FL trained on RSD against central trained on clinical labels, and FL trained on clinical labels against central trained on RSD (P = 0.046, P = 0.126, P = 0.224, and P = 0.0173, respectively). Four of the 7 (57%) models trained on local institutional data performed inferiorly to the FL models. The model performance for local models was positively correlated with the label agreement (between clinical and RSD labels, CC = 0.389, P = 0.387), total number of plus cases (CC = 0.759, P = 0.047), and overall training set size (CC = 0.924, P = 0.002). CONCLUSIONS: We found that a trained FL model performs comparably to a centralized model, confirming that FL may provide an effective, more feasible solution for interinstitutional learning. Smaller institutions benefit more from collaboration than larger institutions, showing the potential of FL for addressing disparities in resource access.

Neurodevelopmental outcomes in preterm infants with retinopathy of prematurity.

Over the past decade there has been a paradigm shift in the treatment of retinopathy of prematurity (ROP) with the introduction of antivascular endothelial growth factor (anti-VEGF) treatments. Anti-VEGF agents have the advantages of being easier to administer, requiring less anesthesia, having the potential for improved peripheral vision, and producing less refractive error than laser treatment. On the other hand, it is known that intravitreal administration of anti-VEGF agents lowers VEGF levels in the blood and raises the theoretical concern of intraocular anti-VEGF causing deleterious effects in other organ systems, including the brain. As a result, there has been increased attention recently on neurodevelopmental outcomes in infants treated with anti-VEGF agents. These studies should be put into context with what is known about systemic comorbidities, socioeconomic influences, and the effects of extreme prematurity itself on neurodevelopmental outcomes. We summarize what is known about neurodevelopmental outcomes in extremely preterm infants with ROP, discuss the implications for determining the neurodevelopmental status using neurodevelopmental testing as well as other indicators, and review the existing literature relating to neurodevelopmental outcomes in babies treated for ROP.

Aggressive posterior retinopathy of prematurity in two cohorts of patients in South India: implications for primary, secondary, and tertiary prevention.

BACKGROUND: Aggressive posterior retinopathy of prematurity (APROP), which has a poor visual prognosis, is common in low- and middle-income countries (LMICs) as a result of suboptimal oxygen monitoring (primary prevention). The purpose of this study was to compare outcomes in APROP eyes treated with laser to eyes treated with antivascular endothelial growth factor (anti-VEGF) therapy. METHODS: The medical records of a cohort of APROP eyes treated with anti-VEGF (2010-2018) and another of eyes treated with laser photocoagulation (2002-2010) at the same institution in South India were reviewed retrospectively and compared. The main outcome was the proportion of eyes developing retinal detachment during resolution of acute ROP. RESULTS: A total of 398 eyes of 199 preterm babies with APROP were included: 168 eyes were treated with photocoagulation; 230, with anti-VEGF. From 2002 to 2010, compared to the more recent cohort, babies diagnosed with APROP tended to be heavier (P < 0.001), older (P < 0.001), and exposed to fewer days of oxygen (P = 0.02). In the laser-treated cohort, 17 of 168 eyes (10%) developed retinal detachment (7, stage 5; 12, stage 4), compared with 3 of 230 (1%) in the anti-VEGF cohort (all stage 4 [P = 0.002]). CONCLUSIONS: The incidence of retinal detachment was significantly lower in eyes treated with anti-VEGF compared with laser-.treated eyes In the absence of a randomized trial, these data suggest that anti-VEGF may lead to better anatomic outcomes, although questions remain concerning dosage, timing, and risks.

Artificial intelligence and deep learning in ophthalmology.

Artificial intelligence (AI) based on deep learning (DL) has sparked tremendous global interest in recent years. DL has been widely adopted in image recognition, speech recognition and natural language processing, but is only beginning to impact on healthcare. In ophthalmology, DL has been applied to fundus photographs, optical coherence tomography and visual fields, achieving robust classification performance in the detection of diabetic retinopathy and retinopathy of prematurity, the glaucoma-like disc, macular oedema and age-related macular degeneration. DL in ocular imaging may be used in conjunction with telemedicine as a possible solution to screen, diagnose and monitor major eye diseases for patients in primary care and community settings. Nonetheless, there are also potential challenges with DL application in ophthalmology, including clinical and technical challenges, explainability of the algorithm results, medicolegal issues, and physician and patient acceptance of the AI 'black-box' algorithms. DL could potentially revolutionise how ophthalmology is practised in the future. This review provides a summary of the state-of-the-art DL systems described for ophthalmic applications, potential challenges in clinical deployment and the path forward.

Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity.

BACKGROUND: Prior work has demonstrated the near-perfect accuracy of a deep learning retinal image analysis system for diagnosing plus disease in retinopathy of prematurity (ROP). Here we assess the screening potential of this scoring system by determining its ability to detect all components of ROP diagnosis. METHODS: Clinical examination and fundus photography were performed at seven participating centres. A deep learning system was trained to detect plus disease, generating a quantitative assessment of retinal vascular abnormality (the i-ROP plus score) on a 1-9 scale. Overall ROP disease category was established using a consensus reference standard diagnosis combining clinical and image-based diagnosis. Experts then ranked ordered a second data set of 100 posterior images according to overall ROP severity. RESULTS: 4861 examinations from 870 infants were analysed. 155 examinations (3%) had a reference standard diagnosis of type 1 ROP. The i-ROP deep learning (DL) vascular severity score had an area under the receiver operating curve of 0.960 for detecting type 1 ROP. Establishing a threshold i-ROP DL score of 3 conferred 94% sensitivity, 79% specificity, 13% positive predictive value and 99.7% negative predictive value for type 1 ROP. There was strong correlation between expert rank ordering of overall ROP severity and the i-ROP DL vascular severity score (Spearman correlation coefficient=0.93; p<0.0001). CONCLUSION: The i-ROP DL system accurately identifies diagnostic categories and overall disease severity in an automated fashion, after being trained only on posterior pole vascular morphology. These data provide proof of concept that a deep learning screening platform could improve objectivity of ROP diagnosis and accessibility of screening.

Ultra-Wide-Field Fundus Autofluorescence and Spectral-Domain Optical Coherence Tomography Findings in Syphilitic Outer Retinitis.

BACKGROUND AND OBJECTIVE: To determine the ultra-wide-field fundus autofluorescence (UWFFAF) and optical coherence tomography (OCT) features of syphilitic outer retinopathy (SOR). PATIENTS AND METHODS: Retrospective chart review. RESULTS: Three patients with SOR were investigated. Treatment with parenteral penicillin led to improvement of outer retinopathy, visual acuity, and symptoms. UWFFAF showed speckled hyperautofluorescence, hypoautofluorescence, and normal autofluorescence, similar to what has been described as a trizonal pattern in acute zonal occult outer retinopathy (AZOOR) in the chronic case of SOR, but with hyperautofluorescent areas in the two acute cases. OCT showed disruption of the photoreceptor outer segment ellipsoid zone and external limiting membrane, which improved after penicillin treatment, and corresponded to normalization of the hyperautofluorescent areas on UWFFAF. There was irregularity and nodular thickening of retinal pigment epithelium on OCT in areas of mottled hyperautofluorescence. CONCLUSION: SOR can present similarly to AZOOR on UWFFAF and should be highly suspected in cases presenting like AZOOR. [Ophthalmic Surg Lasers Imaging Retina. 2017;48:208-215. ].

Wide-field retinal imaging in the management of noninfectious posterior uveitis.

PURPOSE: To determine whether the use of ultra wide-field imaging changes the management or determination of disease activity in patients with noninfectious posterior uveitis. DESIGN: Prospective, observational case series. METHODS: setting: Divisions of Retina and Ocular Immunology at single academic medical center. patient population: Total of 43 patients with noninfectious posterior uveitis seen by 4 investigators at the Wilmer Eye Institute. procedures: Each patient underwent standard clinical examination, followed by ultra wide-field scanning laser ophthalmoscope (SLO) imaging and angiography. Investigators successively determined disease activity and management decisions based on clinical examination, examination plus simulated 30- or 60-degree fluorescein angiography (FA) (obtained by physically narrowing the field of view of the wide-field images), examination plus ultra wide-field SLO images, and examination plus wide-field FA. main outcome measures: The primary outcome was the percentage of patients whose management changed based on the availability of wide-field imaging, compared with standard examination and imaging. The secondary outcome was detection of disease activity with and without wide-angle imaging. RESULTS: Management was altered in 7 of 43 patients (16%) based on examination and limited FA, whereas 21 of 43 patients (48%) had management change with the use of the ultra wide-field imaging and angiography (P < .001). Disease activity was detected in 22 of 43 patients (51%) based on examination and simulated conventional imaging, and in 27 of 43 (63%) with wide-field imaging (P = .27). CONCLUSIONS: The index study, with several design limitations, has suggested that ultra wide-field imaging may alter management decisions compared to standard-of-care imaging and clinical examination. Additional studies, including longitudinal evaluations, are needed to determine whether these findings, or the subsequent management alterations, may improve patient outcomes.