Development of a deep learning system to detect glaucoma using macular vertical optical coherence tomography scans of myopic eyes

Abstract

Myopia is one of the risk factors for glaucoma, making accurate diagnosis of glaucoma in myopic eyes particularly important. However, diagnosis of glaucoma in myopic eyes is challenging due to the frequent associations of distorted optic disc and distorted parapapillary and macular structures. Macular vertical scan has been suggested as a useful tool to detect glaucomatous retinal nerve fiber layer loss even in highly myopic eyes. The present study was performed to develop and validate a deep learning (DL) system to detect glaucoma in myopic eyes using macular vertical optical coherence tomography (OCT) scans and compare its diagnostic power with that of circumpapillary OCT scans. The study included a training set of 1416 eyes, a validation set of 471 eyes, a test set of 471 eyes, and an external test set of 249 eyes. The ability to diagnose glaucoma in eyes with large myopic parapapillary atrophy was greater with the vertical than the circumpapillary OCT scans, with areas under the receiver operating characteristic curves of 0.976 and 0.914, respectively. These findings suggest that DL artificial intelligence based on macular vertical scans may be a promising tool for diagnosis of glaucoma in myopic eyes.