Understanding required to consider AI applications to the field of ophthalmology

Abstract

Applications of artificial intelligence technology, especially deep learning, in ophthalmology research have started with the diagnosis of diabetic retinopathy and have now expanded to all areas of ophthalmology, mainly in the identification of fundus diseases such as glaucoma and age-related macular degeneration. In addition to fundus photography, optical coherence tomography is often used as an imaging device. In addition to simple binary classification, region identification (segmentation model) is used as an identification method for interpretability. Furthermore, there have been AI applications in the area of regression estimation, which is different from diagnostic identification. While expectations for deep learning AI are rising, regulatory agencies have begun issuing guidance on the medical applications of AI. The reason behind this trend is that there are a number of existing issues regarding the application of AI that need to be considered, including, but not limited to, the handling of personal information by large technology companies, the black-box issue, the flaming issue, the theory of responsibility, and issues related to improving the performance of commercially available AI. Furthermore, researchers have reported that there are a plethora of issues that simply cannot be solved by the high performance of artificial intelligence models, such as educating users and securing the communication environment, which are just a few of the necessary steps toward the actual implementation process of an AI society. Multifaceted perspectives and efforts are needed to create better ophthalmology care through AI.