Purpose: This article explores the application of artificial intelligence (AI) in the differentiation of choroidal melanocytic lesions, specifically choroidal nevi and small melanomas, within the field of ocular oncology. The primary topic highlights the significance of accurately diagnosing these lesions to enhance patient outcomes and management strategies. Design: The study reviews of the role of AI in differentiating choroidal melanocytic lesions, particularly choroidal nevi from small melanomas, examining clinical and imaging risk factors. It explores deep learning (DL) applications for image classification and assesses AI's potential impact on patient care, diagnostic accuracy, and regulatory concerns in ocular oncology. Methods: To achieve this, the methods discussed in this paper revolve around employing DL techniques, which utilize artificial neural networks to analyze high-dimensional medical images. This approach enables automated classification and image analysis of ophthalmic data, allowing for the identification of intricate patterns and features that may be imperceptible to clinicians. Additionally, the text reviews existing clinical and imaging risk factors associated with the growth of choroidal nevi into melanoma, leveraging this information to inform and enhance AI algorithms. Results: The anticipated results of integrating AI into clinical practice include increased diagnostic accuracy, which can lead to earlier identification of high-risk lesions and, consequently, timely interventions. This proactive approach has the potential to improve patient care significantly by facilitating better management strategies, thus enhancing patient outcomes. Artificial intelligence may also uncover subtle imaging features that would otherwise be overlooked, providing a more comprehensive assessment of lesions. Conclusion: In conclusion, the paper emphasizes the transformative potential of AI in ocular oncology, advocating for its integration with existing imaging technologies. While AI offers promising advancements in diagnostic practices and patient care, the paper also acknowledges the necessity of addressing regulatory and implementation challenges to fully harness these benefits. Overall, the incorporation of AI technologies into the diagnostic workflow has the potential to not only save vision but also improve survival rates, marking a significant step forward in the management of choroidal melanocytic lesions. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Purpose: The purpose of this study was to describe a case of Nocardia chorioretinitis-related choroidal neovascularization (CNV) in a patient with anti-GM-CSF antibodies with resolution of choroidal neovascularization and visual recovery following a series of intravitreal anti-vascular endothelial growth factor. Methods: This study is a case report. Results: In our case, a 50-year-old female, thought to be immunocompetent, presented with metamorphopsia and decreased visual acuity in the left eye in the setting of disseminated Nocardiosis. She had evidence of a subfoveal Nocardia lesion with subretinal fluid and CNV. Following a series of off-label injections with aflibercept, the patient had improvement in lesion size, exudation, and visual acuity. Extensive workup yielded underlying immunocompromise due to presence of anti-GM-CSF antibodies, likely predisposing her to disseminated Nocardiosis. Conclusion: The use of aflibercept in Nocardia chorioretinitis led to resolution of neovascular activity with visual recovery in a patient with disseminated Nocardiosis.

Importance Tumor thickness is a well-established risk factor for malignant transformation of choroidal nevus into melanoma. To date, reliable evaluation of tumor thickness relies on B-scan ultrasonography, which is frequently unavailable at nonsubspecialty clinics where most melanocytic choroidal lesions (MCLs) are first diagnosed. Objective To describe a technique for potential rapid and reliable estimation of MCL thickness using only Optomap ultra-widefield (UWF) images without B-scan ultrasonography. Design, Setting, and Participants This retrospective, exploratory, cross-sectional analysis of consecutive MCLs diagnosed at Byers Eye Institute, Stanford University, Palo Alto, California, investigates the quantitative correlation between B-scan ultrasonographic thickness of MCLs with the relative pixel intensity of MCLs on green-channel (GC) Optomap UWF images. Pixel intensity overlying the lesion was standardized to the pixel intensity surrounding the lesion (pixel intensity difference [PID]), which was then correlated with ultrasonographic tumor thickness in all study lesions using linear regression analysis. Data were collected from January 1, 2019, to July 1, 2021. Main Outcomes and Measures The correlation between ultrasonographic tumor thickness and PID was measured. Performance (sensitivity and specificity) of the regression analysis trendline in estimating tumor thickness was also determined. Results A total of 138 MCLs from 138 patients (mean age, 57.0 years; 51% female) were included, comprising 125 that were nevi and 13 that were melanoma. The mean ultrasonographic tumor thickness was 1.1 mm (median, 0.8 mm; range, 0.2-5.5 mm), with a mean PID of 2.13. Stratifying lesions by ultrasonographic thickness (<1.0 mm vs 1.0-2.0 mm vs >2.0 mm), the mean PID increased (-1.95 vs 3.72 vs 17.62; P < .001) as mean thickness increased (0.5 mm vs 1.4 mm vs 3.3 mm; P < .001). PID was correlated with tumor thickness (R-2 = 0.823; 95% CI, 0.770-0.875; P < .001) across lesions of all sizes. Conclusions and Relevance In this proof-of-principle study, GC-derived lesion intensity correlated well with ultrasonographic tumor thickness. Leveraging this correlation, this study demonstrates a technique for potentially reliable and rapid estimation of tumor thickness using UWF Optomap images without the use of B-scan ultrasonography.

PURPOSE OF REVIEW:The current article provides an overview of the utility of artificial intelligence approaches to aid in the design, recruitment, execution, and dissemination of ophthalmic clinical trials. RECENT FINDINGS:Within the last decade, artificial intelligence has heralded a new age for ophthalmology, with novel applications habitually appearing within the literature. Though clinical trials are considered the gold standard for driving evidence-based practice, remarkably few studies have examined the potential for machine learning to augment the clinical trial pipeline. Clinical trials within ophthalmology often do not reach planned endpoints due to insufficient enrolment, cost overruns, and can lack reliability from unblinded outcome assessors. Ones that do, frequently take longer to enroll patients than intended. Artificial intelligence-based approaches have recently been shown to be effective in identifying eligible clinical trial participants using both imaging and text data. SUMMARY:Given the key role of clinical trials in the advancement of ophthalmic clinical practice, trialists should consider the potential for artificial intelligence-powered tools to enhance the design, recruitment, and delivery of future studies.

Artificial intelligence (AI) is a growing area that relies on the heavy use of diagnostic imaging within the field of retina to offer exciting advancements in diagnostic capability to better understand and manage retinal conditions such as diabetic retinopathy, diabetic macular edema, age-related macular degeneration, and retinopathy of prematurity. However, there are discrepancies between the findings of these AI programs and their referral recommendations compared with evidence-based referral patterns, such as Preferred Practice Patterns by the American Academy of Ophthalmology. The overall focus of this task force report is to first describe the work in AI being completed in the management of retinal conditions. This report also discusses the guidelines of the Preferred Practice Pattern and how they can be used in the emerging field of AI.

Purpose of review The current article provides an overview of the present approaches to algorithm validation, which are variable and largely self-determined, as well as solutions to address inadequacies. Recent findings In the last decade alone, numerous machine learning applications have been proposed for ophthalmic diagnosis or disease monitoring. Remarkably, of these, less than 15 have received regulatory approval for implementation into clinical practice. Although there exists a vast pool of structured and relatively clean datasets from which to develop and test algorithms in the computational ‘laboratory’, real-world validation remains key to allow for safe, equitable, and clinically reliable implementation. Bottlenecks in the validation process stem from a striking paucity of regulatory guidance surrounding safety and performance thresholds, lack of oversight on critical postdeployment monitoring and context-specific recalibration, and inherent complexities of heterogeneous disease states and clinical environments. Implementation of secure, third-party, unbiased, pre and postdeployment validation offers the potential to address existing shortfalls in the validation process. Summary Given the criticality of validation to the algorithm pipeline, there is an urgent need for developers, machine learning researchers, and end-user clinicians to devise a consensus approach, allowing for the rapid introduction of safe, equitable, and clinically valid machine learning implementations.

Importance Democratizing artificial intelligence (AI) enables model development by clinicians with a lack of coding expertise, powerful computing resources, and large, well-labeled data sets.Objective To determine whether resource-constrained clinicians can use self-training via automated machine learning (ML) and public data sets to design high-performing diabetic retinopathy classification models.Design, Setting, and Participants This diagnostic quality improvement study was conducted from January 1, 2021, to December 31, 2021. A self-training method without coding was used on 2 public data sets with retinal images from patients in France (Messidor-2 [n = 1748]) and the UK and US (EyePACS [n = 58 689]) and externally validated on 1 data set with retinal images from patients of a private Egyptian medical retina clinic (Egypt [n = 210]). An AI model was trained to classify referable diabetic retinopathy as an exemplar use case. Messidor-2 images were assigned adjudicated labels available on Kaggle; 4 images were deemed ungradable and excluded, leaving 1744 images. A total of 300 images randomly selected from the EyePACS data set were independently relabeled by 3 blinded retina specialists using the International Classification of Diabetic Retinopathy protocol for diabetic retinopathy grade and diabetic macular edema presence; 19 images were deemed ungradable, leaving 281 images. Data analysis was performed from February 1 to February 28, 2021.Exposures Using public data sets, a teacher model was trained with labeled images using supervised learning. Next, the resulting predictions, termed pseudolabels, were used on an unlabeled public data set. Finally, a student model was trained with the existing labeled images and the additional pseudolabeled images.Main Outcomes and Measures The analyzed metrics for the models included the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and F1 score. The Fisher exact test was performed, and 2-tailed P values were calculated for failure case analysis.Results For the internal validation data sets, AUROC values for performance ranged from 0.886 to 0.939 for the teacher model and from 0.916 to 0.951 for the student model. For external validation of automated ML model performance, AUROC values and accuracy were 0.964 and 93.3% for the teacher model, 0.950 and 96.7% for the student model, and 0.890 and 94.3% for the manually coded bespoke model, respectively.Conclusions and Relevance These findings suggest that self-training using automated ML is an effective method to increase both model performance and generalizability while decreasing the need for costly expert labeling. This approach advances the democratization of AI by enabling clinicians without coding expertise or access to large, well-labeled private data sets to develop their own AI models.

This study aimed to evaluate the image quality assessment (IQA) and quality criteria employed in publicly available datasets for diabetic retinopathy (DR). A literature search strategy was used to identify relevant datasets, and 20 datasets were included in the analysis. Out of these, 12 datasets mentioned performing IQA, but only eight specified the quality criteria used. The reported quality criteria varied widely across datasets, and accessing the information was often challenging. The findings highlight the importance of IQA for AI model development while emphasizing the need for clear and accessible reporting of IQA information. The study suggests that automated quality assessments can be a valid alternative to manual labeling and emphasizes the importance of establishing quality standards based on population characteristics, clinical use, and research purposes. In conclusion, image quality assessment is important for AI model development; however, strict data quality standards must not limit data sharing. Given the importance of IQA for developing, validating, and implementing deep learning (DL) algorithms, it’s recommended that this information be reported in a clear, specific, and accessible way whenever possible. Automated quality assessments are a valid alternative to the traditional manual labeling process, and quality standards should be determined according to population characteristics, clinical use, and research purpose.

Background and ObjectivesCadaveric studies have shown disease-related neurodegeneration and other morphological abnormalities in the retina of individuals with Parkinson disease (PD); however, it remains unclear whether this can be reliably detected with in vivo imaging. We investigated inner retinal anatomy, measured using optical coherence tomography (OCT), in prevalent PD and subsequently assessed the association of these markers with the development of PD using a prospective research cohort.MethodsThis cross-sectional analysis used data from 2 studies. For the detection of retinal markers in prevalent PD, we used data from AlzEye, a retrospective cohort of 154,830 patients aged 40 years and older attending secondary care ophthalmic hospitals in London, United Kingdom, between 2008 and 2018. For the evaluation of retinal markers in incident PD, we used data from UK Biobank, a prospective population-based cohort where 67,311 volunteers aged 40-69 years were recruited between 2006 and 2010 and underwent retinal imaging. Macular retinal nerve fiber layer (mRNFL), ganglion cell-inner plexiform layer (GCIPL), and inner nuclear layer (INL) thicknesses were extracted from fovea-centered OCT. Linear mixed-effects models were fitted to examine the association between prevalent PD and retinal thicknesses. Hazard ratios for the association between time to PD diagnosis and retinal thicknesses were estimated using frailty models.ResultsWithin the AlzEye cohort, there were 700 individuals with prevalent PD and 105,770 controls (mean age 65.5 +/- 13.5 years, 51.7% female). Individuals with prevalent PD had thinner GCIPL (-2.12 mu m, 95% CI -3.17 to -1.07, p = 8.2 x 10-5) and INL (-0.99 mu m, 95% CI -1.52 to -0.47, p = 2.1 x 10-4). The UK Biobank included 50,405 participants (mean age 56.1 +/- 8.2 years, 54.7% female), of whom 53 developed PD at a mean of 2,653 +/- 851 days. Thinner GCIPL (hazard ratio [HR] 0.62 per SD increase, 95% CI 0.46-0.84, p = 0.002) and thinner INL (HR 0.70, 95% CI 0.51-0.96, p = 0.026) were also associated with incident PD.DiscussionIndividuals with PD have reduced thickness of the INL and GCIPL of the retina. Involvement of these layers several years before clinical presentation highlight a potential role for retinal imaging for at-risk stratification of PD.

IMPORTANCE Telemedicine is accelerating the remote detection and monitoring of medical conditions, such as vision-threatening diseases. Meaningful deployment of smartphone apps for home vision monitoring should consider the barriers to patient uptake and engagement and address issues around digital exclusion in vulnerable patient populations. OBJECTIVE To quantify the associations between patient characteristics and clinical measures with vision monitoring app uptake and engagement. DESIGN, SETTING, AND PARTICIPANTS In this cohort and survey study, consecutive adult patients attending Moorfields Eye Hospital receiving intravitreal injections for retinal disease between May 2020 and February 2021 were included. EXPOSURES Patients were offered the Home Vision Monitor (HVM) smartphone app to self-test their vision. A patient survey was conducted to capture their experience. App data, demographic characteristics, survey results, and clinical data from the electronic health record were analyzed via regression and machine learning. MAIN OUTCOMES AND MEASURES Associations of patient uptake, compliance, and use rate measured in odds ratios (ORs). RESULTS Of 417 included patients, 236 (56.6%) were female, and the mean (SD) age was 72.8 (12.8) years. A total of 258 patients (61.9%) were active users. Uptake was negatively associated with age (OR, 0.98; 95% CI, 0.97-0.998; P =.02) and positively associated with both visual acuity in the better-seeing eye (OR, 1.02; 95% CI, 1.00-1.03; P =.01) and baseline number of intravitreal injections (OR, 1.01; 95% CI, 1.00-1.02; P =.02). Of 258 active patients, 166 (64.3%) fulfilled the definition of compliance. Compliance was associated with patients diagnosed with neovascular age-related macular degeneration (OR, 1.94; 95% CI, 1.07-3.53; P =.002), White British ethnicity (OR, 1.69; 95% CI, 0.96-3.01; P =.02), and visual acuity in the better-seeing eye at baseline (OR, 1.02; 95% CI, 1.01-1.04; P =.04). Use rate was higher with increasing levels of comfort with use of modern technologies (beta = 0.031; 95% CI, 0.007-0.055; P =.02). A total of 119 patients (98.4%) found the app either easy or very easy to use, while 96 (82.1%) experienced increased reassurance from using the app. CONCLUSIONS AND RELEVANCE This evaluation of home vision monitoring for patients with common vision-threatening disease within a clinical practice setting revealed demographic, clinical, and patient-related factors associated with patient uptake and engagement. These insights inform targeted interventions to address risks of digital exclusion with smartphone-based medical devices.

The source of subretinal or intraretinal fluid in patients with optic disc pit maculopathy (ODP-M) remains unclear and is often thought to be either vitreous or cerebrospinal fluid.1 Here, we present the case of a 40-year-old man who developed ODP-M. Further imaging with wide-field swept-source optical coherence tomography demonstrated that the macular fluid was tracking from a nasal optic disc pit with superonasal communication to the vitreous. This suggests that swept-source optical coherence tomography can be a useful tool for determining the origin of macular fluid in patients with ODP-M. [Ophthalmic Surg Lasers Imaging Retina 2022;53:579-581.].

Treatment outcomes in retinopathy of prematurity (ROP) are closely correlated with the location (i.e. zone) of disease, with more posterior zones having poorer outcomes. The most posterior zone, Zone I, is defined as a circle centered on the optic nerve with radius twice the distance from nerve to fovea, or subtending an angle of 30 degrees. Because the eye enlarges and undergoes refractive changes during the period of ROP screening, the absolute area of Zone I according to these definitions may likewise change. It is possible that these differences may confound accurate assessment of risk in patients with ROP. In this study, we estimated the area of Zone I in relation to different ocular parameters to determine how variability in the size and refractive power of the eye may affect zoning. Using Gaussian optics, a model was constructed to calculate the absolute area of Zone I as a function of corneal power, anterior chamber depth, lens power, lens thickness, and axial length (AL), with Zone I defined as a circle with radius set by a 30-degree visual angle. Our model predicted Zone I area to be most sensitive to changes in AL; for example, an increase of AL from 14.20 to 16.58 mm at postmenstrual age 32 weeks was calculated to expand the area of Zone I by up to 72%. These findings motivate several hypotheses which upon future testing may help optimize treatment decisions for ROP.

Natural language processing (NLP) is a subfield of machine intelligence focused on the interaction of human language with computer systems. NLP has recently been discussed in the mainstream media and the literature with the advent of Generative Pre-trained Transformer 3 (GPT-3), a language model capable of producing human-like text. The release of GPT-3 has also sparked renewed interest on the applicability of NLP to contemporary healthcare problems. This article provides an overview of NLP models, with a focus on GPT-3, as well as discussion of applications specific to ophthalmology. We also outline the limitations of GPT-3 and the challenges with its integration into routine ophthalmic care.

A 58-year-old male who underwent cataract extraction with combined intraocular lens and Hydrus® Microstent (Ivantis Inc, Irvine, CA, US) implantation 2 years ago in the right eye (OD) due to advanced glaucoma presented with blurry vision in right eye (OD) for 3 months. The visual acuity was 20/60 and slit-lamp examination indicated mild anterior chamber inflammation with unexposed, functioning tube shunt superotemporally in OD. Optical coherence tomography demonstrated cystoid macular edema (CME) with subretinal fluid. Fluorescein angiography demonstrated petaloid pattern leakage of CME. Gonioscopy revealed a kinked appearance of a Hydrus® Microstent protruding into the anterior chamber and causing iris chafing. Topical ketorolac tromethamine and prednisolone acetate were started. At the 2nd month of follow-up, the anterior chamber was quiet, and the CME resolved completely. Protruded kinked Hydrus® Microstent may lead to acute iridocyclitis and CME through iris chafing, which may be responsive to topical anti-inflammatory drops.