Accuracy of Using Generative Adversarial Networks for Glaucoma Detection: Systematic Review and Bibliometric Analysis

Abstract

Background: Glaucoma leads to irreversible blindness. Globally, it is the second most common retinal disease that leads to blindness, slightly less common than cataracts. Therefore, there is a great need to avoid the silent growth of this disease using recently developed generative adversarial networks (GANs).

Objective: This paper aims to introduce a GAN technology for the diagnosis of eye disorders, particularly glaucoma. This paper illustrates deep adversarial learning as a potential diagnostic tool and the challenges involved in its implementation. This study describes and analyzes many of the pitfalls and problems that researchers will need to overcome to implement this kind of technology.

Methods: To organize this review comprehensively, articles and reviews were collected using the following keywords: ("Glaucoma," "optic disc," "blood vessels") and ("receptive field," "loss function," "GAN," "Generative Adversarial Network," "Deep learning," "CNN," "convolutional neural network" OR encoder). The records were identified from 5 highly reputed databases: IEEE Xplore, Web of Science, Scopus, ScienceDirect, and PubMed. These libraries broadly cover the technical and medical literature. Publications within the last 5 years, specifically 2015-2020, were included because the target GAN technique was invented only in 2014 and the publishing date of the collected papers was not earlier than 2016. Duplicate records were removed, and irrelevant titles and abstracts were excluded. In addition, we excluded papers that used optical coherence tomography and visual field images, except for those with 2D images. A large-scale systematic analysis was performed, and then a summarized taxonomy was generated. Furthermore, the results of the collected articles were summarized and a visual representation of the results was presented on a T-shaped matrix diagram. This study was conducted between March 2020 and November 2020.

Results: We found 59 articles after conducting a comprehensive survey of the literature. Among the 59 articles, 30 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences. The other 29 articles discuss the recent advances in GANs, do practical experiments, and contain analytical studies of retinal disease.

Conclusions: Recent deep learning techniques, namely GANs, have shown encouraging performance in retinal disease detection. Although this methodology involves an extensive computing budget and optimization process, it saturates the greedy nature of deep learning techniques by synthesizing images and solves major medical issues. This paper contributes to this research field by offering a thorough analysis of existing works, highlighting current limitations, and suggesting alternatives to support other researchers and participants in further improving and strengthening future work. Finally, new directions for this research have been identified.

Keywords: blood vessels; deep learning; generative adversarial network; glaucoma; optic disc; retinal disease; systematic literature review.

Figure 1

Fundus image structure.

Figure 2

GAN architecture. GAN: generative adversarial network.

Figure 3

Flowchart of the study selection with the research query and inclusion criteria. GAN: generative adversarial network; WOS: Web of Science.

Figure 4

Scope validation diagram.

Figure 5

Taxonomy of the literature on glaucoma screening based GANs technique. cGAN: conditional GAN; CNN: convolutional neural network; DCGAN: deep convolutional generative adversarial network; DL: deep learning; GAN: generative adversarial network; LSGAN: least-square GAN; WGAN-GP: Wasserstein GAN-gradient penalty.

Figure 6

Distribution of papers per landmark(s). BG: background; BV, blood vessel; OC: optic cup; OD: optic disc; RL: rim loss; RNFL: retinal nerve fiber layer.

Figure 7

Total use of various datasets in glaucoma screening.

Figure 8

Distribution of papers per libraries. WOS: Web of Science.

Figure 9

Distribution of frequently used evaluation metrics in glaucoma screening. AUC: area under the curve; BLE: Boundary Distance Localization Error; IoU: Intersection over Union; ISC: Image Structure Clustering; MCC: Matthews correlation coefficient; mAP: Mean Average Precision; MIoU: Mean Intersection over Union; PSNR: peak signal-to-noise ratio; ROC: receiver operating characteristic curve; SSIM: structural index similarity.

Figure 10

Challenges of glaucoma screening using GANs technique. AL: artificial learning; GAN: generative adversarial network.

Figure 11

Benefits of GANs-based methods for glaucoma screening. DCNN: deep convolutional neural network; GAN: generative adversarial network.

Figure 12

Recommendations of using GANs-based methods in glaucoma screening. AI: artificial intelligence; CAD: computed-aided design; GAN: generative adversarial network; OC: optic cup; OD: optic disc; VAEGAN: variational autoencoder with GAN.