Kang NY, Ra H, Lee K, et al. - In the present study, the researchers sought to examine the feasibility of using deep learning (DL) models to classify pachychoroid and non-pachychoroid eyes from optical coherence tomography (OCT) B-scan images. A total of 1,898 OCT B-scan images were obtained from eyes with macular diseases. Model performance was evaluated using an independent test set of 50 non-pachychoroid and 50 pachychoroid images. Pachychoroid and non-pachychoroid images with good output were categorized by DL models. Using CNN models of deep rather than shallow neural networks, accurate classification can be achieved.