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.

Real-time line-field optical coherence tomography for cellular resolution imaging of biological tissue.

A real-time line-field optical coherence tomography (LF-OCT) system is demonstrated with image acquisition rates of up to 5000 B-frames or 2.5 million A-lines per second for 500 A-lines per B-frame. The system uses a high-speed low-cost camera to achieve continuous data transfer rates required for real-time imaging, allowing the evaluation of future applications in clinical or intraoperative environments. The light source is an 840 nm super-luminescent diode. Leveraging parallel computing with GPU and high speed CoaXPress data transfer interface, we were able to acquire, process, and display OCT data with low latency. The studied system uses anamorphic beam shaping in the detector arm, optimizing the field of view and sensitivity for imaging biological tissue at cellular resolution. The lateral and axial resolution measured in air were 1.7 µm and 6.3 µm, respectively. Experimental results demonstrate real-time inspection of the trabecular meshwork and Schlemm's canal on ex vivo corneoscleral wedges and real-time imaging of endothelial cells of human subjects in vivo.

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.

Conjunctival Lesions Secondary to Systemic Varicella Zoster Virus Infection.

Purpose: To report and present images of a case in which discrete conjunctival lesions developed in the setting of primary varicella zoster virus infection (ie, chickenpox). Methods: Case report and literature review. Results: This report describes a young, unvaccinated male who developed an acutely painful, red eye in the setting of disseminated primary varicella zoster infection. The cutaneous rash was widespread and included lesions on both eyelids. The patient was found to have multiple discrete de-epithelialized lesions involving the palpebral and bulbar conjunctiva. Throughout the disease course, good visual function was maintained and there was no evidence of intraocular involvement. The ocular surface lesions resolved without sequelae after 1 week of treatment with topical antibiotic ointment. Conclusions: Primary varicella zoster infection is an increasingly rare phenomenon in the setting of widespread vaccination. However, unvaccinated or undervaccinated individuals and other at-risk populations remain susceptible to developing severe infections. This case of chickenpox involved discrete conjunctival lesions that resolved without sequelae after conservative treatment with topical antibiotic ointment. While serious ophthalmic complications are uncommon in primary varicella infection, clinicians should be aware of the potential for ocular morbidity in this increasingly rare condition.

Rubella virus-associated necrotizing granulomatous inflammation with extensive eyelid, ocular, and orbital involvement.

We present a case of cutaneous granulomatous disease associated with rubella virus in a 4-year-old girl without an identifiable immunodeficiency. In this case, a combination of anti-inflammatory, anti-viral, and anti-neutrophil therapies successfully treated vision-threatening eyelid, conjunctival, scleral, and orbital inflammation.

Human MPox (Monkeypox) Virus Membranous Keratoconjunctivitis With Transient Corneal Hypoesthesia and Late Symblepharon Formation: A Novel Case and Clinical Implications.

PURPOSE: The aim of this study was to describe a case of corneal involvement as an early manifestation of ocular disease in the 2022 human mpox (monkeypox) virus outbreak. METHODS: This is a single case report with longitudinal care. RESULTS: A 47-year-old immunocompetent man presented with viral conjunctivitis before development of skin lesions or systemic symptoms. Subsequently, he developed membranous keratoconjunctivitis and a corneal epithelial defect. Orthopoxvirus-positive polymerase chain reaction test from his ocular surface was positive. The epithelial defect did not heal with conservative treatment but was successfully treated with amniotic membrane transplantation over 8 days. Reduced corneal sensation was noted after epithelial healing, and polymerase chain reaction from the ocular surface remained positive at 17 days from symptom onset, with slowly recovering conjunctivitis at 21 days. Continued membrane formation required repeated removal but significantly improved with topical corticosteroid treatment after epithelial healing by 29 days of symptom onset. Corneal sensation normalized by 87 days from symptom onset at which time symblepharon were noted but PCR testing from the ocular surface was negative. CONCLUSIONS: Early corneal involvement of human monkeypox virus is possible. Transient corneal hypoesthesia may be due to acute inflammation. Chronic inflammatory changes can result in symblepharon. These findings have potential implications in patient care and corneal donation.

Assistive applications of artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: Assistive (nonautonomous) artificial intelligence (AI) models designed to support (rather than function independently of) clinicians have received increasing attention in medicine. This review aims to highlight several recent developments in these models over the past year and their ophthalmic implications. RECENT FINDINGS: Artificial intelligence models with a diverse range of applications in ophthalmology have been reported in the literature over the past year. Many of these systems have reported high performance in detection, classification, prognostication, and/or monitoring of retinal, glaucomatous, anterior segment, and other ocular pathologies. SUMMARY: Over the past year, developments in AI have been made that have implications affecting ophthalmic surgical training and refractive outcomes after cataract surgery, therapeutic monitoring of disease, disease classification, and prognostication. Many of these recently developed models have obtained encouraging results and have the potential to serve as powerful clinical decision-making tools pending further external validation and evaluation of their generalizability.

Deep Convolutional Neural Networks Detect no Morphological Differences Between Culture-Positive and Culture-Negative Infectious Keratitis Images.

Purpose: To determine whether convolutional neural networks can detect morphological differences between images of microbiologically positive and negative corneal ulcers. Methods: A cross-sectional comparison of prospectively collected data consisting of bacterial and fungal cultures and smears from eyes with acute infectious keratitis at Aravind Eye Hospital. Two convolutional neural network architectures (DenseNet and MobileNet) were trained using images obtained from handheld cameras collected from culture-positive and negative images and smear-positive and -negative images. Each architecture was trained on two image sets: (1) one with labels assigned using only culture results and (2) one using culture and smear results. The outcome measure was area under the receiver operating characteristic curve for predicting whether an ulcer would be microbiologically positive or negative. Results: There were 1970 images from 886 patients were included. None of the models were better than random chance at predicting positive microbiologic results (area under the receiver operating characteristic curve ranged from 0.49 to 0.56; all confidence intervals included 0.5). Conclusions: These two state-of-the-art deep convolutional neural network architectures could not reliably predict whether a corneal ulcer would be microbiologically positive or negative based on clinical photographs. This absence of detectable morphological differences informs the future development of computer vision models trained to predict the causative agent in infectious keratitis using corneal photography. Translational Relevance: These deep learning models were not able to identify morphological differences between microbiologically positive and negative corneal ulcers. This finding suggests that similar artificial intelligence models trained to identify the causative pathogen using only microbiologically positive cases may have potential to generalize well, including to cases with falsely negative microbiologic testing.

Alternaria fungus growing on top of cyanoacrylate glue in a patient with perforated corneal ulcer.

Purpose: To demonstrate a case where Alternaria fungus grew on top of cyanoacrylate glue used to seal a perforated corneal ulcer. Observations: We document the clinical course of a rare case of Alternaria keratitis over the course of 6 months. Despite the purported antifungal properties of cyanoacrylate glue demonstrated in vitro, this case provides in vivo evidence that this substance can serve as a scaffold on which pathogenic fungi may grow. Conclusion: This report demonstrates the importance of close follow up of patients with corneal glue patches in place. Ophthalmologists should continue to inspect the cornea and glue for possible development of secondary infection, particularly with concomitant contact lens and/or steroid use.

Practice Patterns and Clinician Opinions for Treatment of Ocular Rosacea.

PURPOSE: Management of ocular rosacea is challenged by the limited evidence-based systemic treatment guidelines and lack of elucidated mechanisms of treatment efficacy. METHODS: We conducted an online survey of clinicians who regularly treat ocular rosacea to elicit their opinions on treatment algorithms and understanding of the treatment's primary mechanism of action. Descriptive statistics and univariate comparisons were reported. RESULTS: One hundred thirty-two participants completed the online survey. Of the 132 respondents, 74% were cornea specialists. Most respondents (85%) favored systemic tetracyclines over macrolides. Providers' specialty training did not significantly influence preference between tetracyclines and macrolides for ocular rosacea management. Among tetracycline prescribers, there was no consensus regarding initial dosage and duration prescribing patterns. Most macrolide prescribers (88%) initiated a 3-week course of 1 gram of azithromycin weekly. Long-term management strategy for treatment-responsive patients varied: 46% preferred to half the initial dose, 29% discontinued pharmacotherapy, and 16% chronically pulse-dosed patients. Most tetracycline prescribers (90%) and macrolide prescribers (73%) postulate their chosen agents' primary mechanism of effect for ocular rosacea is anti-inflammatory. However, there was no consensus in identifying anti-inflammatory doses of either drug class. Furthermore, there is discordance between prescribers' intended mechanistic effect with the selection of initial dosages for both tetracycline and macrolides for ocular rosacea. CONCLUSIONS: Among clinicians who commonly treat ocular rosacea, there is significant community equipoise regarding which dose of tetracycline is best for initial systemic treatment of this disease. In addition, a consensus understanding regarding mechanism of action of this treatment is lacking.

Image-Based Differentiation of Bacterial and Fungal Keratitis Using Deep Convolutional Neural Networks.

Purpose: Develop computer vision models for image-based differentiation of bacterial and fungal corneal ulcers and compare their performance against human experts. Design: Cross-sectional comparison of diagnostic performance. Participants: Patients with acute, culture-proven bacterial or fungal keratitis from 4 centers in South India. Methods: Five convolutional neural networks (CNNs) were trained using images from handheld cameras collected from patients with culture-proven corneal ulcers in South India recruited as part of clinical trials conducted between 2006 and 2015. Their performance was evaluated on 2 hold-out test sets (1 single center and 1 multicenter) from South India. Twelve local expert cornea specialists performed remote interpretation of the images in the multicenter test set to enable direct comparison against CNN performance. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) individually and for each group collectively (i.e., CNN ensemble and human ensemble). Results: The best-performing CNN architecture was MobileNet, which attained an AUC of 0.86 on the single-center test set (other CNNs range, 0.68-0.84) and 0.83 on the multicenter test set (other CNNs range, 0.75-0.83). Expert human AUCs on the multicenter test set ranged from 0.42 to 0.79. The CNN ensemble achieved a statistically significantly higher AUC (0.84) than the human ensemble (0.76; P < 0.01). CNNs showed relatively higher accuracy for fungal (81%) versus bacterial (75%) ulcers, whereas humans showed relatively higher accuracy for bacterial (88%) versus fungal (56%) ulcers. An ensemble of the best-performing CNN and best-performing human achieved the highest AUC of 0.87, although this was not statistically significantly higher than the best CNN (0.83; P = 0.17) or best human (0.79; P = 0.09). Conclusions: Computer vision models achieved superhuman performance in identifying the underlying infectious cause of corneal ulcers compared with cornea specialists. The best-performing model, MobileNet, attained an AUC of 0.83 to 0.86 without any additional clinical or historical information. These findings suggest the potential for future implementation of these models to enable earlier directed antimicrobial therapy in the management of infectious keratitis, which may improve visual outcomes. Additional studies are ongoing to incorporate clinical history and expert opinion into predictive models.

Corneal imaging with blue-light optical coherence microscopy.

Corneal imaging is important for the diagnostic and therapeutic evaluation of many eye diseases. Optical coherence tomography (OCT) is extensively used in ocular imaging due to its non-invasive and high-resolution volumetric imaging characteristics. Optical coherence microscopy (OCM) is a technical variation of OCT that can image the cornea with cellular resolution. Here, we demonstrate a blue-light OCM as a low-cost and easily reproducible system to visualize corneal cellular structures such as epithelial cells, endothelial cells, keratocytes, and collagen bundles within stromal lamellae. Our blue-light OCM system achieved an axial resolution of 12 µm in tissue over a 1.2 mm imaging depth, and a lateral resolution of 1.6 µm over a field of view of 750 µm × 750 µm.

Neonatal corneal ulcer secondary to congenital entropion.

PURPOSE: To describe a case of central corneal ulceration in a newborn secondary to congenital entropion. OBSERVATIONS: Corneal ulcers during infancy are rare and may occur secondary to congenital structural anomalies, including congenital entropion. Correct anatomic eyelid position in newborns is challenging to determine with closed eyelids, and eyelid squeezing during crying and discomfort adds to this challenge. CONCLUSIONS AND IMPORTANCE: This report reinforces the importance of careful examination of the adnexa in infants with corneal ulcers while they are most comfortable, usually after topical anesthesia and prior to placement of eyelid speculum. Ophthalmologists caring for infants must be able to detect this condition because prompt entropion repair is necessary for corneal ulcer resolution and prevention of permanent vision loss.

Very late onset LASIK flap Acremonium fungal keratitis confirmed by metagenomic deep sequencing.

PURPOSE: To describe a unique case of LASIK flap fungal keratitis confirmed by next generation sequencing. OBSERVATIONS: A 56-year-old female presented with refractory keratitis involving her LASIK flap 21 years after surgery. Confocal was positive for filamentous structures. The patient underwent immediate flap amputation followed by topical antifungal treatment. Corneal culture was positive for Acremonium sp. Metagenomic deep sequencing confirmed Acremonium as the primary source of infection and also identified Fusarium as a likely contributor of a mixed fungal infection. Sequencing also identified hay as the likely source of the infection. Treatment resulted in eradication of the infection. The patient's final best corrected visual acuity was 20/30 with rigid contact lens overrefraction. CONCLUSIONS: Metagenomic deep sequencing is a novel diagnostic tool that is increasingly being utilized for diagnosis of refractory keratitis. This case demonstrates the diagnostic potential of deep sequencing for identifying post-LASIK keratitis and reinforces the utility of LASIK flap amputation in the setting of tectonic flap instability due to keratolysis. IMPORTANCE: This case highlights several important clinical points for treating LASIK flap keratitis and highlights the emerging role metagenomic sequencing has in the diagnosis of infectious keratitis. This is first known case using next generation sequencing to diagnose a post-LASIK infectious keratitis.

MULTIMODAL IMAGING OF TWO UNCONVENTIONAL CASES OF BARTONELLA NEURORETINITIS.

PURPOSE: To report two cases of cat-scratch fever with atypical posterior segment manifestations. METHODS: Two cases were retrospectively reviewed. RESULTS: A 27-year-old woman presented with painless blurring of central vision in her left eye. Clinical examination revealed a small focal area of retinitis within the macula associated with a subtle macular star. Spectral-domain optical coherence tomography showed a hyper-reflective inner retinal lesion in addition to subretinal and intraretinal fluid as well as hyperreflective foci within the outer plexiform layer. Serology was positive for anti-B. henselae IgM (titer 1:32). A 34-year-old woman presented with painless loss of vision in both eyes associated with headaches and pain with extraocular movement. Spectral-domain optical coherence tomography depicted subretinal fluid, intraretinal fluid, and hyperreflective deposits within the outer plexiform layer. A focal collection of vitreous cell was observed overlying the optic nerve in the left eye. Bilateral disk leakage was identified on fluorescein angiography. Serology revealed high-titer anti-B. henselae antibodies (IgM titers 1:32, IgG titers 1:256). CONCLUSION: Our cases highlight the necessity of recognizing more unusual posterior segment presentations of ocular bartonellosis. Multimodal retinal imaging including spectral-domain optical coherence tomography may help better characterize lesions.

Differentiation of Active Corneal Infections from Healed Scars Using Deep Learning.

PURPOSE: To develop and evaluate an automated, portable algorithm to differentiate active corneal ulcers from healed scars using only external photographs. DESIGN: A convolutional neural network was trained and tested using photographs of corneal ulcers and scars. PARTICIPANTS: De-identified photographs of corneal ulcers were obtained from the Steroids for Corneal Ulcers Trial (SCUT), Mycotic Ulcer Treatment Trial (MUTT), and Byers Eye Institute at Stanford University. METHODS: Photographs of corneal ulcers (n = 1313) and scars (n = 1132) from the SCUT and MUTT were used to train a convolutional neural network (CNN). The CNN was tested on 2 different patient populations from eye clinics in India (n = 200) and the Byers Eye Institute at Stanford University (n = 101). Accuracy was evaluated against gold standard clinical classifications. Feature importances for the trained model were visualized using gradient-weighted class activation mapping. MAIN OUTCOME MEASURES: Accuracy of the CNN was assessed via F1 score. The area under the receiver operating characteristic (ROC) curve (AUC) was used to measure the precision-recall trade-off. RESULTS: The CNN correctly classified 115 of 123 active ulcers and 65 of 77 scars in patients with corneal ulcer from India (F1 score, 92.0% [95% confidence interval (CI), 88.2%-95.8%]; sensitivity, 93.5% [95% CI, 89.1%-97.9%]; specificity, 84.42% [95% CI, 79.42%-89.42%]; ROC: AUC, 0.9731). The CNN correctly classified 43 of 55 active ulcers and 42 of 46 scars in patients with corneal ulcers from Northern California (F1 score, 84.3% [95% CI, 77.2%-91.4%]; sensitivity, 78.2% [95% CI, 67.3%-89.1%]; specificity, 91.3% [95% CI, 85.8%-96.8%]; ROC: AUC, 0.9474). The CNN visualizations correlated with clinically relevant features such as corneal infiltrate, hypopyon, and conjunctival injection. CONCLUSIONS: The CNN classified corneal ulcers and scars with high accuracy and generalized to patient populations outside of its training data. The CNN focused on clinically relevant features when it made a diagnosis. The CNN demonstrated potential as an inexpensive diagnostic approach that may aid triage in communities with limited access to eye care.

Impact of Sample Collection Order on the Diagnostic Performance of Metagenomic Deep Sequencing for Infectious Keratitis.

PURPOSE: The purpose of this article was to evaluate the impact of sample collection order on the diagnostic yield of metagenomic deep sequencing (MDS) for determining the causative pathogen in infectious keratitis. METHODS: We performed a cross-sectional diagnostic test evaluation among subjects with infectious keratitis at Aravind Eye Hospital in Madurai, India. All subjects underwent corneal scrapings of the affected eye to obtain potassium hydroxide smear, Gram stain, bacterial culture, and fungal culture, in this order. The order of MDS specimen collection relative to smear and culture samples was randomized and served as the primary predictor. Outcomes included the normalized copy number of pathogenic RNA detected by MDS, the proportion of MDS samples that were diagnostic, and the agreement of MDS results with cultures. RESULTS: MDS samples from 46 subjects with corneal ulcers were evaluated. MDS was positive in 33 subjects (76%) and had 74% overall agreement with culture results. There was no association between order of MDS sample collection and normalized copy number of genetic material detected (P = 0.62) or the likelihood of MDS positivity (P = 0.46). However, the likelihood of agreement between MDS and cultures decreased when MDS corneal swabs were collected after other diagnostic corneal scrapings (P = 0.05). CONCLUSIONS: The overall yield of MDS for detecting the cause of infectious keratitis was not affected by sample collection order. However, diagnostic agreement between MDS and cultures decreased when MDS samples were collected after other specimens. Additional investigation is warranted to determine whether this represents increased sensitivity of MDS compared with cultures or higher susceptibility to contaminants.