A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression

Abstract

Because of recent advances in computing technology and the availability of large datasets, deep learning has risen to the forefront of artificial intelligence, with performances that often equal, or sometimes even exceed, those of human subjects on a variety of tasks, especially those related to image classification and pattern recognition. As one of the medical fields that is highly dependent on ancillary imaging tests, ophthalmology has been in a prime position to witness the application of deep learning algorithms that can help analyze the vast amount of data coming from those tests. In particular, glaucoma stands as one of the conditions where application of deep learning algorithms could potentially lead to better use of the vast amount of information coming from structural and functional tests evaluating the optic nerve and macula. The purpose of this article is to critically review recent applications of deep learning models in glaucoma, discussing their advantages but also focusing on the challenges inherent to the development of such models for screening, diagnosis and detection of progression. After a brief general overview of deep learning and how it compares to traditional machine learning classifiers, we discuss issues related to the training and validation of deep learning models and how they specifically apply to glaucoma. We then discuss specific scenarios where deep learning has been proposed for use in glaucoma, such as screening with fundus photography, and diagnosis and detection of glaucoma progression with optical coherence tomography and standard automated perimetry.

Translational relevance: Deep learning algorithms have the potential to significantly improve diagnostic capabilities in glaucoma, but their application in clinical practice requires careful validation, with consideration of the target population, the reference standards used to build the models, and potential sources of bias.

Keywords: deep learning; glaucoma; optical coherence tomography; visual fields.

Figure 1.

A diagram showing the organization of the classification of machine learning algorithms.

Figure 2.

Schematic representation of “neurons” on an artificial neural network. The input data corresponds to the data one it trying to classify. The number of neurons in the input layer will depend on the input data (e.g., number of pixels in an image). These input neurons are then connected to neurons in hidden layers. There may be many hidden layers, which can be quite complex depending on the type of model. For convolutional neural networks, the hidden layers are of the convolutional type, specializing in spatial patterns. Finally, all calculations will converge to a final model prediction in the output layer.

Figure 3.

Examples of optic disc photographs and corresponding actual SDOCT measurements of average RNFL. Above each photo are also shown the DL prediction of average RNFL thickness from the optic disc photograph by the M2M algorithm. Note that the predictions from the DL algorithm can be quite close to actual SDOCT RNFL thickness measurements for a variety of photos. Adapted from Medeiros et al..

Figure 4.

Class activation maps (CAM) for several examples of deep learning models. (A) Gradient-weighted CAM from the M2M model to predict RNFL thickness from fundus photographs. It can be seen that the heatmap correctly highlights the area of the optic nerve and adjacent RNFL as most relevant for the predictions. (adapted from Medeiros et al.²⁴). (B) Gradient-weighted CAM map from the M2M model used to predict rim width in an eye with glaucoma. Note that the heatmap strongly highlights the cup and rim regions. (adapted from Thompson et al.²⁶). (C) CAM showing the regions in a spectral-domain optical coherence tomography volume identified as the most important for the classification of the scan into healthy versus glaucoma. For glaucoma eyes the map generally highlighted regions that agree with established clinical markers for glaucoma diagnosis, such as the optic disc cup and neuroretinal rim. It should be noted, however, that the highlighted areas are often very broad, sometimes extending even to the vitreous (adapted from Maetschke et al.⁶⁶).