Development and Validation of a Deep Learning System for Diagnosing Glaucoma Using Optical Coherence Tomography

Abstract

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.

Keywords: deep learning system; diagnostic ability; ganglion cell–inner plexiform layer; glaucoma; retinal nerve fiber layer; spectral-domain optical coherence tomography.

Figure 1

Schematic overview of the proposed deep learning model of convolutional neural network (CNN)-based visual geometry group deep (VGG-19) architecture. The input data were a stack of two-dimensional images (176 × 176 pixel) composed of four optical coherence tomography images (thickness and deviation maps of retinal nerve fiber layer (RNFL) and ganglion cell–inner plexiform layer (GCIPL) analyses) and a matrix image with an ocular axial length value.

Figure 2

Area under the receiver operating characteristic curve (AUROC) of a deep learning system for glaucoma diagnosis based on a retinal nerve fiber layer thickness map of spectral-domain optical coherence tomography, in comparison with that of glaucoma specialists.

Figure 3

Heatmaps highlighting the region of high probability for glaucoma diagnosis were generated to validate the deep learning system using retinal nerve fiber layer (RNFL) and ganglion cell–inner plexiform layer (GCIPL) thickness maps of spectral-domain optical coherence tomography. Images are representative RNFL and GCIPL thickness maps and corresponding heatmaps for which the deep learning system produce predictions resulting in (A,B) excellent, (C,D) partial, and (E,F) no agreement with glaucoma specialists on RNFL and GCIPL defect locations. A. Glaucoma specialists confirmed superotemporal and inferotemporal RNFL defect from the RNFL thickness map; the heatmap showed that the deep learning system detected the same lesion, showing high agreement between them. B. Glaucoma specialists and the heatmap agreed on an inferotemporal GCIPL defect. C. Superotemporal and inferotemporal RNFL defects were confirmed by glaucoma specialists, but only the inferotemporal lesion was demonstrated on the heatmap, thus showing partial agreement. D. A whole inferior GCIPL defect was confirmed by a glaucoma specialist, but only part of the lesion was shown on the heatmap. E. Discrepancy between the colored lesion on the heatmap and the thin, superotemporal RNFL defect detected by glaucoma specialists, showing no agreement. F. A thin, inferotemporal GCIPL defect was confirmed by glaucoma specialists, but the heatmap showed an irrelevant lesion.