Isolated retinal neovascularization in retinopathy of prematurity: clinical associations and prognostic implications.

OBJECTIVE: Isolated retinal neovascularization (IRNV) is a common finding in patients with stage 2 and 3 retinopathy of prematurity (ROP). This study aims to further classify the clinical course and significance of these lesions (previously described as "popcorn" based on clinical appearance) in patients with ROP as visualized with ultra-widefield optical coherence tomography (UWF-OCT). DESIGN: Single center, retrospective case series. PARTICIPANTS: Images were collected from 136 babies in the Oregon Health and Science University neonatal intensive care unit. METHODS: A prototype UWF-OCT device captured en face scans (>140°), which were reviewed for the presence of IRNV along with standard zone, stage, and plus classification. In a cross-sectional analysis we compared demographics and the clinical course of eyes with and without IRNV. Longitudinally, we compared ROP severity using a clinician-assigned vascular severity score (VSS) and compared the risk of progression among eyes with and without IRNV using multivariable logistic regression (MLR). MAIN OUTCOME MEASURES: Differences in clinical demographics and disease progression between patients with and without IRNV. RESULTS: Of the 136 patients, 60 developed stage 2 or worse ROP during their disease course, 22 of whom had IRNV visualized on UWF-OCT (37%). On average, patients with IRNV had lower birth weights (BW) (660.1g vs 916.8g, p = 0.001), gestational age (GA) (24.9 vs 26.1 weeks, p = 0.01), and were more likely to present with ROP in zone I (63.4% vs 15.8%, p < 0.001). They were also more likely to progress to stage 3 (68.2% vs 13.2%, p < 0.001) and receive treatment (54.5% vs 15.8%, p = 0.002). Eyes with IRNV had a higher peak VSS (5.61 vs 3.73, p < 0.001) and averaged a higher VSS throughout their disease course. On MLR, IRNV was independently associated with progression to stage 3 (p = 0.02) and requiring treatment (p = 0.03), controlling for GA, BW, and initial zone 1 disease. CONCLUSION: In this single center study, we found that IRNV occurs in higher risk babies and was an independent risk factor for ROP progression and treatment. These findings may have implications for OCT-based ROP classifications in the future.

P-Score: A Reference-Image-Based Clinical Grading Scale for Vascular Change in Retinopathy of Prematurity.

PURPOSE: The International Classification of Retinopathy of Prematurity Third Edition (ICROP3) acknowledged that plus-like ROP vascular changes occur along a spectrum. Historically, clinician-experts demonstrate variable agreement for plus diagnosis. We developed a 9-photo reference-image set for grading plus-like changes and compared intergrader agreement of the set to standard grading with no-plus/pre-plus/plus. DESIGN: Retinal photographic grading and expert consensus opinion PARTICIPANTS: Development: 34 international ICROP3 committee members. VALIDATION: 30 ophthalmologists with ROP expertise (15 ICROP3 committee members, 15 non-ICROP3 members) METHODS: Nine ROP fundus images (P1 through P9) representing increasing degrees of zone I vascular tortuosity and dilation, based on ICROP3-committee's 34 members' gradings and consensus image review, were used to establish standard photographs for the "Plus (P) Score." Study participants graded 150 fundus photographs two ways, separated by a 1-week washout period: (1) no-plus/pre-plus/plus disease, (2) choosing the closest P-Score image. MAIN OUTCOME MEASURES: Intergrader agreement measured by intraclass correlation coefficient (ICC) RESULTS: Intergrader agreement was higher using P-Score (ICC 0.75, 95% CI 0.71-0.79) than no-plus/pre-plus/plus (ICC 0.67, 95% CI 0.62-0.72). Mean P-Scores for images whose mode gradings were no-plus, pre-plus, and plus, were 2.5 (SD 0.7), 4.8 (SD 0.8), and 7.4 (SD 0.8), respectively. CONCLUSIONS: Intergrader agreement of plus-like vascular change in ROP using the P-Score is high. We recommend incorporation of this 9-image reference set into ICROP3 and clinician daily practice alongside zone/stage/plus. P-score is not yet meant to replace plus diagnosis for treatment decisions, but its use at our institutions has permitted better comparison between examinations for progression and regression, communication between examiners, and documentation of vascular change without fundus imaging. P-score also could provide more detailed ROP classification for clinical trials, consistent with the spectrum of plus-like change that is now formally part of ICROP.

Multinational External Validation of Autonomous Retinopathy of Prematurity Screening.

Importance: Retinopathy of prematurity (ROP) is a leading cause of blindness in children, with significant disparities in outcomes between high-income and low-income countries, due in part to insufficient access to ROP screening. Objective: To evaluate how well autonomous artificial intelligence (AI)-based ROP screening can detect more-than-mild ROP (mtmROP) and type 1 ROP. Design, Setting, and Participants: This diagnostic study evaluated the performance of an AI algorithm, trained and calibrated using 2530 examinations from 843 infants in the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) study, on 2 external datasets (6245 examinations from 1545 infants in the Stanford University Network for Diagnosis of ROP [SUNDROP] and 5635 examinations from 2699 infants in the Aravind Eye Care Systems [AECS] telemedicine programs). Data were taken from 11 and 48 neonatal care units in the US and India, respectively. Data were collected from January 2012 to July 2021, and data were analyzed from July to December 2023. Exposures: An imaging processing pipeline was created using deep learning to autonomously identify mtmROP and type 1 ROP in eye examinations performed via telemedicine. Main Outcomes and Measures: The area under the receiver operating characteristics curve (AUROC) as well as sensitivity and specificity for detection of mtmROP and type 1 ROP at the eye examination and patient levels. Results: The prevalence of mtmROP and type 1 ROP were 5.9% (91 of 1545) and 1.2% (18 of 1545), respectively, in the SUNDROP dataset and 6.2% (168 of 2699) and 2.5% (68 of 2699) in the AECS dataset. Examination-level AUROCs for mtmROP and type 1 ROP were 0.896 and 0.985, respectively, in the SUNDROP dataset and 0.920 and 0.982 in the AECS dataset. At the cross-sectional examination level, mtmROP detection had high sensitivity (SUNDROP: mtmROP, 83.5%; 95% CI, 76.6-87.7; type 1 ROP, 82.2%; 95% CI, 81.2-83.1; AECS: mtmROP, 80.8%; 95% CI, 76.2-84.9; type 1 ROP, 87.8%; 95% CI, 86.8-88.7). At the patient level, all infants who developed type 1 ROP screened positive (SUNDROP: 100%; 95% CI, 81.4-100; AECS: 100%; 95% CI, 94.7-100) prior to diagnosis. Conclusions and Relevance: Where and when ROP telemedicine programs can be implemented, autonomous ROP screening may be an effective force multiplier for secondary prevention of ROP.

Development of a Semi-automated Computer-based Tool for the Quantification of Vascular Tortuosity in the Murine Retina.

Purpose: The murine oxygen-induced retinopathy (OIR) model is one of the most widely used animal models of ischemic retinopathy, mimicking hallmark pathophysiology of initial vaso-obliteration (VO) resulting in ischemia that drives neovascularization (NV). In addition to NV and VO, human ischemic retinopathies, including retinopathy of prematurity (ROP), are characterized by increased vascular tortuosity. Vascular tortuosity is an indicator of disease severity, need to treat, and treatment response in ROP. Current literature investigating novel therapeutics in the OIR model often report their effects on NV and VO, and measurements of vascular tortuosity are less commonly performed. No standardized quantification of vascular tortuosity exists to date despite this metric's relevance to human disease. This proof-of-concept study aimed to apply a previously published semi-automated computer-based image analysis approach (iROP-Assist) to develop a new tool to quantify vascular tortuosity in mouse models. Design: Experimental study. Subjects: C57BL/6J mice subjected to the OIR model. Methods: In a pilot study, vasculature was manually segmented on flat-mount images of OIR and normoxic (NOX) mice retinas and segmentations were analyzed with iROP-Assist to quantify vascular tortuosity metrics. In a large cohort of age-matched (postnatal day 12 [P12], P17, P25) NOX and OIR mice retinas, NV, VO, and vascular tortuosity were quantified and compared. In a third experiment, vascular tortuosity in OIR mice retinas was quantified on P17 following intravitreal injection with anti-VEGF (aflibercept) or Immunoglobulin G isotype control on P12. Main Outcome Measures: Vascular tortuosity. Results: Cumulative tortuosity index was the best metric produced by iROP-Assist for discriminating between OIR mice and NOX controls. Increased vascular tortuosity correlated with disease activity in OIR. Treatment of OIR mice with aflibercept rescued vascular tortuosity. Conclusions: Vascular tortuosity is a quantifiable feature of the OIR model that correlates with disease severity and may be quickly and accurately quantified using the iROP-Assist algorithm. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Chorioretinal Anastomosis and Retinal Detachment with Laser Photocoagulation Treated Incontinentia Pigmenti.

PURPOSE: To describe a case of incontinentia pigmenti in which chorioretinal anastomosis occurred after laser photocoagulation, which was ultimately complicated by tractional and rhegmatogenous detachment. METHODS: Observational case report. RESULTS: A 2-month-old was referred to ophthalmology for a rash characteristic of incontinentia pigmenti due to concern for ocular involvement and was found to have peripheral avascular retina with early neovascularization. Following several rounds of panretinal photocoagulation, a chorioretinal anastomosis was noted on follow up fluorescein angiography in the left eye. Subsequently, a tractional retinal detachment formed and was treated initially with a lens sparing pars plana vitrectomy, endolaser, and scleral buckle. Despite treatment, it progressed to a combined tractional/rhegmatogenous detachment and was deemed inoperable. CONCLUSION: Chorioretinal anastomosis is a rare complication of laser photocoagulation.

Genome-wide association identifies novel ROP risk loci in a multiethnic cohort.

We conducted a genome-wide association study (GWAS) in a multiethnic cohort of 920 at-risk infants for retinopathy of prematurity (ROP), a major cause of childhood blindness, identifying 1 locus at genome-wide significance level (p < 5×10-8) and 9 with significance of p < 5×10-6 for ROP ≥ stage 3. The most significant locus, rs2058019, reached genome-wide significance within the full multiethnic cohort (p = 4.96×10-9); Hispanic and European Ancestry infants driving the association. The lead single nucleotide polymorphism (SNP) falls in an intronic region within the Glioma-associated oncogene family zinc finger 3 (GLI3) gene. Relevance for GLI3 and other top-associated genes to human ocular disease was substantiated through in-silico extension analyses, genetic risk score analysis and expression profiling in human donor eye tissues. Thus, we identify a novel locus at GLI3 with relevance to retinal biology, supporting genetic susceptibilities for ROP risk with possible variability by race and ethnicity.

Applications of Deep Learning: Automated Assessment of Vascular Tortuosity in Mouse Models of Oxygen-Induced Retinopathy.

Objective: To develop a generative adversarial network (GAN) to segment major blood vessels from retinal flat-mount images from oxygen-induced retinopathy (OIR) and demonstrate the utility of these GAN-generated vessel segmentations in quantifying vascular tortuosity. Design: Development and validation of GAN. Subjects: Three datasets containing 1084, 50, and 20 flat-mount mice retina images with various stains used and ages at sacrifice acquired from previously published manuscripts. Methods: Four graders manually segmented major blood vessels from flat-mount images of retinas from OIR mice. Pix2Pix, a high-resolution GAN, was trained on 984 pairs of raw flat-mount images and manual vessel segmentations and then tested on 100 and 50 image pairs from a held-out and external test set, respectively. GAN-generated and manual vessel segmentations were then used as an input into a previously published algorithm (iROP-Assist) to generate a vascular cumulative tortuosity index (CTI) for 20 image pairs containing mouse eyes treated with aflibercept versus control. Main Outcome Measures: Mean dice coefficients were used to compare segmentation accuracy between the GAN-generated and manually annotated segmentation maps. For the image pairs treated with aflibercept versus control, mean CTIs were also calculated for both GAN-generated and manual vessel maps. Statistical significance was evaluated using Wilcoxon signed-rank tests (P ≤ 0.05 threshold for significance). Results: The dice coefficient for the GAN-generated versus manual vessel segmentations was 0.75 ± 0.27 and 0.77 ± 0.17 for the held-out test set and external test set, respectively. The mean CTI generated from the GAN-generated and manual vessel segmentations was 1.12 ± 0.07 versus 1.03 ± 0.02 (P = 0.003) and 1.06 ± 0.04 versus 1.01 ± 0.01 (P < 0.001), respectively, for eyes treated with aflibercept versus control, demonstrating that vascular tortuosity was rescued by aflibercept when quantified by GAN-generated and manual vessel segmentations. Conclusions: GANs can be used to accurately generate vessel map segmentations from flat-mount images. These vessel maps may be used to evaluate novel metrics of vascular tortuosity in OIR, such as CTI, and have the potential to accelerate research in treatments for ischemic retinopathies. Financial Disclosures: The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity: Insights from a Multimodal Deep Learning Approach.

Purpose: Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP. Design: Retrospective cohort study. Participants: Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022. Methods: Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO2). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models. Main Outcome Measures: Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score. Results: We found that both daily average and COV of FiO2 were associated with more severe ROP (adjusted P < 0.001). With fivefold cross-validation, the multimodal LSTM models had higher performance than the best static models (SVM using GA and 3 average FiO2 features) and SVM models trained on GA alone (mean AUROC = 0.89 ± 0.04 vs. 0.86 ± 0.05 vs. 0.83 ± 0.04). Conclusions: The development of severe ROP might not only be influenced by oxygen exposure but also by its fluctuation, which provides direction for future study of pathophysiological factors associated with severe ROP development. Additionally, we demonstrated that multimodal neural networks can be a method to extract useful information from time-series data, which may be a valuable methodology for the investigation of other diseases using EHR data. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Assessing the Impact of Image Quality on Deep Learning Classification of Infectious Keratitis.

Objective: To investigate the impact of corneal photograph quality on convolutional neural network (CNN) predictions. Design: A CNN trained to classify bacterial and fungal keratitis was evaluated using photographs of ulcers labeled according to 5 corneal image quality parameters: eccentric gaze direction, abnormal eyelid position, over/under-exposure, inadequate focus, and malpositioned light reflection. Participants: All eligible subjects with culture and stain-proven bacterial and/or fungal ulcers presenting to Aravind Eye Hospital in Madurai, India, between January 1, 2021 and December 31, 2021. Methods: Convolutional neural network classification performance was compared for each quality parameter, and gradient class activation heatmaps were generated to visualize regions of highest influence on CNN predictions. Main Outcome Measures: Area under the receiver operating characteristic and precision recall curves were calculated to quantify model performance. Bootstrapped confidence intervals were used for statistical comparisons. Logistic loss was calculated to measure individual prediction accuracy. Results: Individual presence of either light reflection or eyelids obscuring the corneal surface was associated with significantly higher CNN performance. No other quality parameter significantly influenced CNN performance. Qualitative review of gradient class activation heatmaps generally revealed the infiltrate as having the highest diagnostic relevance. Conclusions: The CNN demonstrated expert-level performance regardless of image quality. Future studies may investigate use of smartphone cameras and image sets with greater variance in image quality to further explore the influence of these parameters on model performance. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Generative Artificial Intelligence Through ChatGPT and Other Large Language Models in Ophthalmology: Clinical Applications and Challenges.

The rapid progress of large language models (LLMs) driving generative artificial intelligence applications heralds the potential of opportunities in health care. We conducted a review up to April 2023 on Google Scholar, Embase, MEDLINE, and Scopus using the following terms: "large language models," "generative artificial intelligence," "ophthalmology," "ChatGPT," and "eye," based on relevance to this review. From a clinical viewpoint specific to ophthalmologists, we explore from the different stakeholders' perspectives-including patients, physicians, and policymakers-the potential LLM applications in education, research, and clinical domains specific to ophthalmology. We also highlight the foreseeable challenges of LLM implementation into clinical practice, including the concerns of accuracy, interpretability, perpetuating bias, and data security. As LLMs continue to mature, it is essential for stakeholders to jointly establish standards for best practices to safeguard patient safety. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Unilateral Exudative Retinal Lesion in a Previously Healthy Female Teenager.

A 15-year-old girl had a 2-month history of decreased vision and a dark spot in the central vision in her right eye. She had a papule on her cheek, intraretinal and subretinal fluid in the central macula, inner retinal thickening, and telangiectasis in the superior macula. What is your diagnosis?

Genome-wide association identifies novel ROP risk loci in a multi-ethnic cohort.

We conducted a genome-wide association study (GWAS) in a multiethnic cohort of 920 at-risk infants for retinopathy of prematurity (ROP), a major cause of childhood blindness, identifying 2 loci at genome-wide significance level (p<5×10-8) and 7 at suggestive significance (p<5×10-6) for ROP ≥ stage 3. The most significant locus, rs2058019, reached genome-wide significance within the full multiethnic cohort (p=4.96×10-9); Hispanic and Caucasian infants driving the association. The lead single nucleotide polymorphism (SNP) falls in an intronic region within the Glioma-associated oncogene family zinc finger 3 (GLI3) gene. Relevance for GLI3 and other top-associated genes to human ocular disease was substantiated through in-silico extension analyses, genetic risk score analysis and expression profiling in human donor eye tissues. Thus, we report the largest ROP GWAS to date, identifying a novel locus at GLI3 with relevance to retinal biology supporting genetic susceptibilities for ROP risk with possible variability by race and ethnicity.

Association of Biomarker-Based Artificial Intelligence With Risk of Racial Bias in Retinal Images.

Importance: Although race is a social construct, it is associated with variations in skin and retinal pigmentation. Image-based medical artificial intelligence (AI) algorithms that use images of these organs have the potential to learn features associated with self-reported race (SRR), which increases the risk of racially biased performance in diagnostic tasks; understanding whether this information can be removed, without affecting the performance of AI algorithms, is critical in reducing the risk of racial bias in medical AI. Objective: To evaluate whether converting color fundus photographs to retinal vessel maps (RVMs) of infants screened for retinopathy of prematurity (ROP) removes the risk for racial bias. Design, Setting, and Participants: The retinal fundus images (RFIs) of neonates with parent-reported Black or White race were collected for this study. A u-net, a convolutional neural network (CNN) that provides precise segmentation for biomedical images, was used to segment the major arteries and veins in RFIs into grayscale RVMs, which were subsequently thresholded, binarized, and/or skeletonized. CNNs were trained with patients' SRR labels on color RFIs, raw RVMs, and thresholded, binarized, or skeletonized RVMs. Study data were analyzed from July 1 to September 28, 2021. Main Outcomes and Measures: Area under the precision-recall curve (AUC-PR) and area under the receiver operating characteristic curve (AUROC) at both the image and eye level for classification of SRR. Results: A total of 4095 RFIs were collected from 245 neonates with parent-reported Black (94 [38.4%]; mean [SD] age, 27.2 [2.3] weeks; 55 majority sex [58.5%]) or White (151 [61.6%]; mean [SD] age, 27.6 [2.3] weeks, 80 majority sex [53.0%]) race. CNNs inferred SRR from RFIs nearly perfectly (image-level AUC-PR, 0.999; 95% CI, 0.999-1.000; infant-level AUC-PR, 1.000; 95% CI, 0.999-1.000). Raw RVMs were nearly as informative as color RFIs (image-level AUC-PR, 0.938; 95% CI, 0.926-0.950; infant-level AUC-PR, 0.995; 95% CI, 0.992-0.998). Ultimately, CNNs were able to learn whether RFIs or RVMs were from Black or White infants regardless of whether images contained color, vessel segmentation brightness differences were nullified, or vessel segmentation widths were uniform. Conclusions and Relevance: Results of this diagnostic study suggest that it can be very challenging to remove information relevant to SRR from fundus photographs. As a result, AI algorithms trained on fundus photographs have the potential for biased performance in practice, even if based on biomarkers rather than raw images. Regardless of the methodology used for training AI, evaluating performance in relevant subpopulations is critical.

Efficacy of Smartphone-Based Telescreening for Retinopathy of Prematurity With and Without Artificial Intelligence in India.

Importance: Retinopathy of prematurity (ROP) telemedicine screening programs have been found to be effective, but they rely on widefield digital fundus imaging (WDFI) cameras, which are expensive, making them less accessible in low- to middle-income countries. Cheaper, smartphone-based fundus imaging (SBFI) systems have been described, but these have a narrower field of view (FOV) and have not been tested in a real-world, operational telemedicine setting. Objective: To assess the efficacy of SBFI systems compared with WDFI when used by technicians for ROP screening with both artificial intelligence (AI) and human graders. Design, Setting, and Participants: This prospective cross-sectional comparison study took place as a single-center ROP teleophthalmology program in India from January 2021 to April 2022. Premature infants who met normal ROP screening criteria and enrolled in the teleophthalmology screening program were included. Those who had already been treated for ROP were excluded. Exposures: All participants had WDFI images and from 1 of 2 SBFI devices, the Make-In-India (MII) Retcam or Keeler Monocular Indirect Ophthalmoscope (MIO) devices. Two masked readers evaluated zone, stage, plus, and vascular severity scores (VSS, from 1-9) in all images. Smartphone images were then stratified by patient into training (70%), validation (10%), and test (20%) data sets and used to train a ResNet18 deep learning architecture for binary classification of normal vs preplus or plus disease, which was then used for patient-level predictions of referral warranted (RW)- and treatment requiring (TR)-ROP. Main Outcome and Measures: Sensitivity and specificity of detection of RW-ROP, and TR-ROP by both human graders and an AI system and area under the receiver operating characteristic curve (AUC) of grader-assigned VSS. Sensitivity and specificity were compared between the 2 SBFI systems using Pearson χ2testing. Results: A total of 156 infants (312 eyes; mean [SD] gestational age, 33.0 [3.0] weeks; 75 [48%] female) were included with paired examinations. Sensitivity and specificity were not found to be statistically different between the 2 SBFI systems. Human graders were effective with SBFI at detecting TR-ROP with a sensitivity of 100% and specificity of 83.49%. The AUCs with grader-assigned VSS only were 0.95 (95% CI, 0.91-0.99) and 0.96 (95% CI, 0.93-0.99) for RW-ROP and TR-ROP, respectively. For the AI system, the sensitivity of detecting TR-ROP sensitivity was 100% with specificity of 58.6%, and RW-ROP sensitivity was 80.0% with specificity of 59.3%. Conclusions and Relevance: In this cross-sectional study, 2 different SBFI systems used by technicians in an ROP screening program were highly sensitive for TR-ROP. SBFI systems with AI may be a cost-effective method to improve the global capacity for ROP screening.

Panretinal Optical Coherence Tomography.

We introduce a new concept of panoramic retinal (panretinal) optical coherence tomography (OCT) imaging system with a 140° field of view (FOV). To achieve this unprecedented FOV, a contact imaging approach was used which enabled faster, more efficient, and quantitative retinal imaging with measurement of axial eye length. The utilization of the handheld panretinal OCT imaging system could allow earlier recognition of peripheral retinal disease and prevent permanent vision loss. In addition, adequate visualization of the peripheral retina has a great potential for better understanding disease mechanisms regarding the periphery. To the best of our knowledge, the panretinal OCT imaging system presented in this manuscript has the widest FOV among all the retina OCT imaging systems and offers significant values in both clinical ophthalmology and basic vision science.

Development and international validation of custom-engineered and code-free deep-learning models for detection of plus disease in retinopathy of prematurity: a retrospective study.

BACKGROUND: Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed through interval screening by paediatric ophthalmologists. However, improved survival of premature neonates coupled with a scarcity of available experts has raised concerns about the sustainability of this approach. We aimed to develop bespoke and code-free deep learning-based classifiers for plus disease, a hallmark of ROP, in an ethnically diverse population in London, UK, and externally validate them in ethnically, geographically, and socioeconomically diverse populations in four countries and three continents. Code-free deep learning is not reliant on the availability of expertly trained data scientists, thus being of particular potential benefit for low resource health-care settings. METHODS: This retrospective cohort study used retinal images from 1370 neonates admitted to a neonatal unit at Homerton University Hospital NHS Foundation Trust, London, UK, between 2008 and 2018. Images were acquired using a Retcam Version 2 device (Natus Medical, Pleasanton, CA, USA) on all babies who were either born at less than 32 weeks gestational age or had a birthweight of less than 1501 g. Each images was graded by two junior ophthalmologists with disagreements adjudicated by a senior paediatric ophthalmologist. Bespoke and code-free deep learning models (CFDL) were developed for the discrimination of healthy, pre-plus disease, and plus disease. Performance was assessed internally on 200 images with the majority vote of three senior paediatric ophthalmologists as the reference standard. External validation was on 338 retinal images from four separate datasets from the USA, Brazil, and Egypt with images derived from Retcam and the 3nethra neo device (Forus Health, Bengaluru, India). FINDINGS: Of the 7414 retinal images in the original dataset, 6141 images were used in the final development dataset. For the discrimination of healthy versus pre-plus or plus disease, the bespoke model had an area under the curve (AUC) of 0·986 (95% CI 0·973-0·996) and the CFDL model had an AUC of 0·989 (0·979-0·997) on the internal test set. Both models generalised well to external validation test sets acquired using the Retcam for discriminating healthy from pre-plus or plus disease (bespoke range was 0·975-1·000 and CFDL range was 0·969-0·995). The CFDL model was inferior to the bespoke model on discriminating pre-plus disease from healthy or plus disease in the USA dataset (CFDL 0·808 [95% CI 0·671-0·909, bespoke 0·942 [0·892-0·982]], p=0·0070). Performance also reduced when tested on the 3nethra neo imaging device (CFDL 0·865 [0·742-0·965] and bespoke 0·891 [0·783-0·977]). INTERPRETATION: Both bespoke and CFDL models conferred similar performance to senior paediatric ophthalmologists for discriminating healthy retinal images from ones with features of pre-plus or plus disease; however, CFDL models might generalise less well when considering minority classes. Care should be taken when testing on data acquired using alternative imaging devices from that used for the development dataset. Our study justifies further validation of plus disease classifiers in ROP screening and supports a potential role for code-free approaches to help prevent blindness in vulnerable neonates. FUNDING: National Institute for Health Research Biomedical Research Centre based at Moorfields Eye Hospital NHS Foundation Trust and the University College London Institute of Ophthalmology. TRANSLATIONS: For the Portuguese and Arabic translations of the abstract see Supplementary Materials section.

Epidemiologic Evaluation of Retinopathy of Prematurity Severity in a Large Telemedicine Program in India Using Artificial Intelligence.

PURPOSE: Epidemiological changes in retinopathy of prematurity (ROP) depend on neonatal care, neonatal mortality, and the ability to carefully titrate and monitor oxygen. We evaluate whether an artificial intelligence (AI) algorithm for assessing ROP severity in babies can be used to evaluate changes in disease epidemiology in babies from South India over a 5-year period. DESIGN: Retrospective cohort study. PARTICIPANTS: Babies (3093) screened for ROP at neonatal care units (NCUs) across the Aravind Eye Care System (AECS) in South India. METHODS: Images and clinical data were collected as part of routine tele-ROP screening at the AECS in India over 2 time periods: August 2015 to October 2017 and March 2019 to December 2020. All babies in the original cohort were matched 1:3 by birthweight (BW) and gestational age (GA) with babies in the later cohort. We compared the proportion of eyes with moderate (type 2) or treatment-requiring (TR) ROP, and an AI-derived ROP vascular severity score (from retinal fundus images) at the initial tele-retinal screening exam for all babies in a district, VSS), in the 2 time periods. MAIN OUTCOME MEASURES: Differences in the proportions of type 2 or worse and TR-ROP cases, and VSS between time periods. RESULTS: Among BW and GA matched babies, the proportion [95% confidence interval {CI}] of babies with type 2 or worse and TR-ROP decreased from 60.9% [53.8%-67.7%] to 17.1% [14.0%-20.5%] (P < 0.001) and 16.8% [11.9%-22.7%] to 5.1% [3.4%-7.3%] (P < 0.001), over the 2 time periods. Similarly, the median [interquartile range] VSS in the population decreased from 2.9 [1.2] to 2.4 [1.8] (P < 0.001). CONCLUSIONS: In South India, over a 5-year period, the proportion of babies developing moderate to severe ROP has dropped significantly for babies at similar demographic risk, strongly suggesting improvements in primary prevention of ROP. These results suggest that AI-based assessment of ROP severity may be a useful epidemiologic tool to evaluate temporal changes in ROP epidemiology. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.