Lee J, Kim JS, Lee HJ, et al. - Researchers examined the performance of a deep learning classifier to distinguish glaucomatous optic neuropathy (GON) from compressive optic neuropathy (CON) based on ganglion cell–inner plexiform layer (GCIPL) and retinal nerve fibre layer (RNFL) spectral-domain optical coherence tomography (SD-OCT). For this study, they gathered 80 SD-OCT image sets from 80 eyes of 80 patients with GON along with 81 SD-OCT image sets from 54 eyes of 54 patients with CON. Predictors used for the deep learning classifier were the bottleneck features extracted from the GCIPL thickness map, GCIPL deviation map, RNFL thickness map and RNFL deviation map. Outcomes support the deep learning classifier as possibly superior to the conventional diagnostic parameters in discrimination of GON and CON on SD-OCT.