Glaucoma is a leading eye disease, causing vision loss by gradually affecting peripheral vision if left untreated. Current diagnosis of glaucoma is performed by ophthalmologists, human experts who typically need to analyze different types of medical images generated by different types of medical equipment: fundus, Retinal Nerve Fiber Layer (RNFL), Optical Coherence Tomography (OCT) disc, OCT macula, perimetry, and/or perimetry deviation. Capturing and analyzing these medical images is labor intensive and time consuming. In this paper, we present a novel approach for glaucoma diagnosis and localization, only relying on fundus images that are analyzed by making use of state-of-the-art deep learning techniques. Specifically, our approach towards glaucoma diagnosis and localization leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), respectively. We built and evaluated different predictive models using a large set of fundus images, collected and labeled by ophthalmologists at Samsung Medical Center (SMC). Our experimental results demonstrate that our most effective predictive model is able to achieve a high diagnosis accuracy of 96%, as well as a high sensitivity of 96% and a high specificity of 100% for Dataset-Optic Disc (OD), a set of center-cropped fundus images highlighting the optic disc. Furthermore, we present Medinoid, a publicly-available prototype web application for computer-aided diagnosis and localization of glaucoma, integrating our most effective predictive model in its back-end.

This study aimed to develop and validate a deep learning system for diagnosing glaucoma using optical coherence tomography (OCT). A training set of 1822 eyes (332 control, 1490 glaucoma) with 7288 OCT images, an internal validation set of 425 eyes (104 control, 321 glaucoma) with 1700 images, and an external validation set of 355 eyes (108 control, 247 glaucoma) with 1420 images were included. Deviation and thickness maps of retinal nerve fiber layer (RNFL) and ganglion cell–inner plexiform layer (GCIPL) analyses were used to develop the deep learning system for glaucoma diagnosis based on the visual geometry group deep convolutional neural network (VGG-19) model. The diagnostic abilities of deep learning models using different OCT maps were evaluated, and the best model was compared with the diagnostic results produced by two glaucoma specialists. The glaucoma-diagnostic ability was highest when the deep learning system used the RNFL thickness map alone (area under the receiver operating characteristic curve (AUROC) 0.987), followed by the RNFL deviation map (AUROC 0.974), the GCIPL thickness map (AUROC 0.966), and the GCIPL deviation map (AUROC 0.903). Among combination sets, use of the RNFL and GCIPL deviation map showed the highest diagnostic ability, showing similar results when tested via an external validation dataset. The inclusion of the axial length did not significantly affect the diagnostic performance of the deep learning system. The location of glaucomatous damage showed generally high level of agreement between the heatmap and the diagnosis of glaucoma specialists, with 90.0% agreement when using the RNFL thickness map and 88.0% when using the GCIPL thickness map. In conclusion, our deep learning system showed high glaucoma-diagnostic abilities using OCT thickness and deviation maps. It also showed detection patterns similar to those of glaucoma specialists, showing promising results for future clinical application as an interpretable computer-aided diagnosis.