Purpose: To predict improvement of best-corrected visual acuity (BCVA) 1 year after pars plana vitrectomy for epiretinal membrane (ERM) using artificial intelligence methods on optical coherence tomography B-scan images.Methods: Four hundred and eleven (411) patients with Stage II ERM were divided in a group improvement (IM) ($15 ETDRS letters of VA recovery) and a group no improvement (N-IM) (,15 letters) according to 1-year VA improvement after 25-G pars plana vitrectomy with internal limiting membrane peeling. Primary outcome was the creation of a deep learning classifier (DLC) based on optical coherence tomography B-scan images for prediction. Secondary outcome was assessment of the influence of various clinical and imaging predictors on BCVA improvement. Inception-ResNet-V2 was trained using standard augmentation techniques. Testing was performed on an external data set. For secondary outcome, B-scan acquisitions were analyzed by graders both before and after fibrillary change processing enhancement.Results: The overall performance of the DLC showed a sensitivity of 87.3% and a specificity of 86.2%. Regression analysis showed a difference in preoperative images prevalence of ectopic inner foveal layer, foveal detachment, ellipsoid zone interruption, cotton wool sign, unprocessed fibrillary changes (odds ratio = 2.75 [confidence interval: 2.49-2.96]), and processed fibrillary changes (odds ratio = 5.42 [confidence interval: 4.81-6.08]), whereas preoperative BCVA and central macular thickness did not differ between groups. Conclusion:The DLC showed high performances in predicting 1-year visual outcome in ERM surgery patients. Fibrillary changes should also be considered as relevant predictors.RETINA 43:173-181, 2023E piretinal membranes (ERMs) are avascular fibro-

Initial stages of Best vitelliform macular dystrophy (BVMD) and adult vitelliform macular dystrophy (AVMD) harbor similar blue autofluorescence (BAF) and optical coherence tomography (OCT) features. Nevertheless, BVMD is characterized by a worse final stage visual acuity (VA) and an earlier onset of critical VA loss. Currently, differential diagnosis requires an invasive and time-consuming process including genetic testing, electrooculography (EOG), full field electroretinogram (ERG), and visual field testing. The aim of our study was to automatically classify OCT and BAF images from stage II BVMD and AVMD eyes using a deep learning algorithm and to identify an image processing method to facilitate human-based clinical diagnosis based on non-invasive tests like BAF and OCT without the use of machine-learning technology. After the application of a customized image processing method, OCT images were characterized by a dark appearance of the vitelliform deposit in the case of BVMD and a lighter inhomogeneous appearance in the case of AVMD. By contrast, a customized method for processing of BAF images revealed that BVMD and AVMD were characterized respectively by the presence or absence of a hypo-autofluorescent region of retina encircling the central hyperautofluorescent foveal lesion. The human-based evaluation of both BAF and OCT images showed significantly higher correspondence to ground truth reference when performed on processed images. The deep learning classifiers based on BAF and OCT images showed around 90% accuracy of classification with both processed and unprocessed images, which was significantly higher than human performance on both processed and unprocessed images. The ability to differentiate between the two entities without recurring to invasive and expensive tests may offer a valuable clinical tool in the management of the two diseases.