New Artificial Intelligence Analysis for Prediction of Long-Term Visual Improvement After Epiretinal Membrane Surgery

Abstract

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-

Variability of Visual Recovery with Time in Epiretinal Membrane Surgery: A Predictive Analysis Based on Retinal Layer OCT Thickness Changes

“…ERM is the most common type of fibrocellular proliferation found at the vitreoretinal interface [ 14 , 15 ]. Since the perfect timing and indication for surgery are still debated, it is of utmost importance to provide the most detailed prognostic information possible before and after the operation.…”

“…An example of how segmentation of retinal layers was performed is shown in Figure 1 . According to variation in BCVA improvement after treatment, the population was further divided into 4 groups, showing either: No variation or improvement < 15 ETDRS letters (3 Snellen lines) [ 14 , 15 ] from preoperative (GROUP 1); or Immediate (1 month after surgery) improvement of visual acuity without further improvements at later follow-ups (GROUP 2); or Immediate (1 month after surgery) improvement of visual acuity with further improvements at later follow-ups (GROUP 3); or Delayed improvement of visual acuity (no or minimal change at 1 month follow-up and >15 ETDRS letter change at 3 or 6 months follow up) (GROUP 4). …”

“…No variation or improvement < 15 ETDRS letters (3 Snellen lines) [ 14 , 15 ] from preoperative (GROUP 1); or…”

Deep learning-based postoperative visual acuity prediction in idiopathic epiretinal membrane

“…Despite similar methods, previous investigation differed in the prediction task assigned to the model. The previous investigation focused on binary classi cation (whether the VA will improve by ≥ 15 letters or not), while our study speci cally aimed to predict the postoperative BCVA (the predicted BCVA could be generated automatically) [31]. To our knowledge, this is the rst report in literature that directly converts the SD-OCT scans to postoperative BCVA.…”

OCT-based deep-learning models for the identification of retinal key signs

“…1 In particular, ML algorithms are powerful tools in the automatic detection and quanti cation of retinal biomarkers identi ed on OCT. [2][3][4] In the last years, different ML models were developed and widely used for the recognition of OCT images acquired on patients with major eye pathologies such as diabetic retinopathy (DR), age-related macular degeneration (AMD), central serous chorioretinopathy (CSC), epiretinal membrane (ERM) and glaucoma. [5][6][7][8][9][10][11][12][13][14][15] Regarding OCT images classi cation, the most used CNN architectures are VGG, ResNet and Inception, and have shown very promising results so far. [16][17][18][19][20] Despite the promising results given by the literature on the use of the VGG-16, ResNet-50, and Inception-v3 architectures for the classi cation of OCT images, the need for large data sets and non-standardized image acquisition techniques limits the applicability of ML in the clinical domain.…”