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

Abstract

Abstract Background To develop a deep learning (DL) model based on preoperative optical coherence tomography (OCT) training to automatically predict the 6-month postoperative visual outcomes in patients with idiopathic epiretinal membrane (iERM). Methods In this retrospective cohort study, a total of 442 eyes (5304 images in total) were enrolled for the development of the DL and multimodal deep fusion network (MDFN) models. All eyes were randomized into a training dataset with 265 eyes (60.0%), a validation dataset with 89 eyes (20.1%), and an external testing dataset with the remaining 88 eyes (19.9%). The input variables for prediction included macular OCT images and various clinical data. Inception-Resnet-v2 network was employed to estimate the 6-month postoperative best-corrected visual acuity (BCVA). The clinical data and OCT parameters were used to develop a regression model for predicting postoperative BCVA. The reliability of the models was further evaluated in the testing dataset. Results The prediction DL algorithm showed a mean absolute error (MAE) of 0.070 logMAR and root mean square error (RMSE) of 0.11 logMAR in the testing dataset. The DL model showed promising performance with R2 = 0.80, compared to R2 = 0.50 of the regression model. The percentages of BCVA prediction errors within ± 0.20 logMAR were 94.32% in the testing dataset. Conclusions The OCT-based DL model demonstrated sensitive and accurate predictive ability of postoperative BCVA in iERM patients. This novel DL model has great potential to be integrated into surgical planning.