Retinal Detachment

Proliferative vitreoretinopathy (PVR) remains the main cause of failure in retinal detachment (RD) surgery and a demanding challenge for vitreoretinal surgeons. Despite the large improvements in surgical techniques and a better understanding of PVR pathogenesis in the last years, satisfactory anatomical and visual outcomes have not been provided yet. For this reason, several different adjunctive pharmacological agents have been investigated in combination with surgery. In this review, we analyze the current and emerging adjunctive treatment options for the management of PVR and we discuss their possible clinical application and beneficial role in this subgroup of patients.

Rhegmatogenous retinal detachment (RRD) is a sight-threatening condition involving retinal detachment and the accumulation of fluid in the subretinal space. Proliferative vitreoretinopathy (PVR) is a pathologic complication that develops after RRD surgery, and approximately 5-10% of RRD cases develop post-operative PVR. Prolonged inflammation in the wound healing process, epithelial-mesenchymal transition (EMT), retinal pigment epithelial (RPE) cell migration and proliferation, and epiretinal, intraretinal, and subretinal fibrosis are typical in the formation of PVR. RPE cells undergo EMT and become fibroblast-like cells that migrate to the retina and vitreous, promoting PVR formation. Fibroblasts transform into myofibroblasts, which promote fibrosis by overproducing the extracellular matrix (ECM). RPE cells, fibroblasts, glial cells, macrophages, T lymphocytes, and increased ECM production form contractile epiretinal membranes. Cytokine release, complement activation, RPE cells, glial cells, and endothelial cells are all involved in retinal immune responses. Normally, wounds heal within 4 to 6 weeks, including hemostasis, inflammation, proliferation, and remodeling phases. Properly initiated inflammation, complement activation, and the function of neutrophils and glial cells heal the wound in the first stage. In a retinal wound, glial cells proliferate and fill the injured area. Gliosis tries to protect the neurons and prevent damage, but it becomes harmful when it causes scarring. If healing is complicated, prolonged inflammation leads to pathological fibrosis. Currently, there is no preventive treatment for the formation of PVR, and it is worth studying in the future.

BackgroundRetinal detachment (RD) is a vision-threatening disorder of significant severity. Individuals with high myopia (HM) face a 2 to 6 times higher risk of developing RD compared to non-myopes. The timely identification of high myopia-related retinal detachment (HMRD) is crucial for effective treatment and prevention of additional vision impairment. Consequently, our objective was to streamline and validate a machine-learning model based on clinical laboratory omics (clinlabomics) for the early detection of RD in HM patients.MethodsWe extracted clinlabomics data from the electronic health records for 24,440 HM and 5607 HMRD between 2015 and 2022. Lasso regression analysis assessed fifty-nine variables, excluding collinear variables (variance inflation factor > 10). Four models based on random forest, gradient boosting machine (GBM), generalized linear model, and Deep Learning Model were trained for HMRD diagnosis and employed for internal validation. An external test of the models was done. Three random data sets were further processed to validate the performance of the diagnostic model. The primary outcomes were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCPR) to diagnose HMRD.ResultsNine variables were selected by all models. Given the AUC and AUCPR values across the different sets, the GBM model was chosen as the final diagnostic model. The GBM model had an AUC of 0.8550 (95%CI = 0.8322-0.8967) and an AUCPR of 0.5584 (95%CI = 0.5250-0.5879) in the training set. The AUC and AUCPR in the internal validation were 0.8405 (95%CI = 0.8060-0.8966) and 0.5355 (95%CI = 0.4988-0.5732). During the external test evaluation, it reached an AUC of 0.7579 (95%CI = 0.7340-0.7840) and an AUCPR of 0.5587 (95%CI = 0.5345-0.5880). A similar discriminative capacity was observed in the three random data sets. The GBM model was well-calibrated across all the sets. The GBM-RD model was implemented into a web application that provides risk prediction for HM individuals.ConclusionGBM algorithms based on nine features successfully predicted the diagnosis of RD in patients with HM, which will help ophthalmologists to establish a preliminary diagnosis and to improve diagnostic accuracy in the clinic.

ObjectiveTo compare ImageNet-pretrained deep convolutional neural networks for automated detection of retinal detachment (RD) in canine fundus photographs.Animals studiedArchived fundus images from 275 dogs.ProceduresIn this multicenter retrospective study, 2000 color fundus photographs (793 RD; 1207 normal) acquired between 2020 and 2025 were included after quality filtering. Data were split at the patient level into training (80%) and an independent validation set (20%). Transfer learning was applied to three pretrained architectures (ResNet50V2, VGG16, EfficientNetB0) using standardized preprocessing and real-time augmentation. Performance on the validation set was assessed using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Ninety-five percent confidence intervals were estimated by bootstrapping.ResultsResNet50V2 achieved the best overall discrimination (accuracy 0.8909; AUC 0.9194), followed by EfficientNetB0 (accuracy 0.8182; AUC 0.8831). VGG16 showed limited reliability (accuracy 0.6182; AUC 0.6868) due to a high false-positive rate. Gradient-weighted class activation mapping indicated that the best-performing model consistently attended to regions consistent with retinal detachment.ConclusionsResNet50V2-based analysis of canine fundus photographs shows strong potential as a scalable screening support tool for RD. Prospective external validation across additional devices and practice settings is warranted before routine clinical implementation.