In Journal of medical Internet research ; h5-index 88.0
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 generative adversarial network 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 five highly reputed databases: IEEE Xplore, Web of Science, Scopus, Science Direct, and PubMed. These libraries broadly cover the technical and medical literature. Among the last five years of publications, only papers within the specified duration were included because the target GAN technique was invented in 2014 by Goodfellow 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 (OCT) and visual field images, except for those with two-dimensional 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 added to multimedia appendix 1 and a visual representation of the results 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, 29 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences. Twenty-nine journal articles discuss recent advances in generative adversarial networks, practical experiments, and analytical studies of retinal disease.
CONCLUSIONS : Recent deep learning techniques, namely, generative adversarial networks, have shown encouraging retinal disease detection performance. 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.
Saeed Ali Q, Sheikh Abdullah Siti Norul Huda, Che-Hamzah Jemaima, Abdul Ghani Ahmad Tarmizi