Purpose To report the first known case of Descemet's Membrane Endothelial Keratoplasty (DMEK) graft rejection following COVID19 infection. Observation A 60-year-old woman with a history of DMEK for Fuch's dystrophy, presented with redness and vision loss in her operated eye 18 months after surgery. Further clinical history revealed systemic symptoms consistent with COVID19, which had started 3 weeks prior to the onset of ocular symptoms. Examination revealed graft rejection, despite patient compliance with maintenance topical corticosteroid therapy. Serological testing was positive for SARS-CoV-2 IgG. The patient responded well to intensive treatment with systemic, periocular and topical corticosteroids, and reversal of graft rejection was achieved. Two months later, there was a recurrence of graft rejection while on maintenance therapy with cyclosporin 2% and topical corticosteroids. The same intensive immunosuppressive treatment protocol was followed, and reversal of graft rejection was again achieved. Conclusion and Importance We believe that COVID-19 infection was a causative factor in this patient DMEK rejection. By highlighting this case, we hope to raise awareness amongst ophthalmologists of potential graft complications following COVID19 infection.

Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches.

Purpose: To evaluate the sensitivity and specificity of ultrawide-field fundus photography (UWF-FP) for the detection and classification of sickle cell retinopathy (SCR) by ophthalmologists with varying degrees of expertise in retinal disease. Methods: Patients presenting with sickle cell disease (SCD) in the Créteil University Eye Clinic, having undergone UWF-FP and ultrawide-field fluorescein angiography (UWF-FA) on the same day, were retrospectively included. Eyes with previous retinal photocoagulation were excluded. SCR was graded independently by UWF-FP and UWF-FA using Goldberg classification by two ophthalmologists with varying expertise levels. Results: Sixty-six eyes of 33 patients were included in the study. The sensitivity of UWF-FP for the detection of proliferative SCR was 100%, (95% confidence interval [CI95%] 76.8–100) for the retinal specialist and 100% (CI95% 71.5–100) for the ophthalmology resident. The specificity of UWF-FP for the detection of proliferative SCR was 100% (CI95% 92.7–100) for the retinal specialist and 98.1% (CI95% 89.7–100) for the ophthalmology resident. Conclusions: UWF-FP is a valuable exam for proliferative SCR screening, with excellent sensitivity and specificity and a good inter-grader agreement for ophthalmologists with various degree of skills, and is easy to use in a real-life setting.

The accurate detection of corneal edema has become a topic of growing interest with the generalization of endothelial keratoplasty. Despite recent advances in deep learning for corneal edema detection, the problem of minimal edema remains challenging. Using transfer learning and a limited training set of 11 images, we built a model to segment the corneal epithelium, which is part of a three-model pipeline to detect corneal edema. A second and a third model are used to detect edema on the stroma alone and on the epithelium. A validation set of 233 images from 30 patients consisting of three groups (Normal, Minimal Edema and important Edema) was used to compare the results of our new pipeline to our previous model. The mean edema fraction (EF), defined as the number of pixels detected as edema divided by the total number of pixels of the cornea, was calculated for each image. With our previous model, the mean EF was not statistically different between the Normal and Minimal Edema groups (p = 0.24). With the current pipeline, the mean EF was higher in the Minimal Edema group compared to the Normal group (p < 0.01). The described pipeline constitutes an adjustable framework for the detection of corneal edema based on optical coherence tomography and yields better performances in cases of minimal or localized edema.