The Role of Medical Image Modalities and AI in the Early Detection, Diagnosis and Grading of Retinal Diseases: A Survey

Abstract

Traditional dilated ophthalmoscopy can reveal diseases, such as age-related macular degeneration (AMD), diabetic retinopathy (DR), diabetic macular edema (DME), retinal tear, epiretinal membrane, macular hole, retinal detachment, retinitis pigmentosa, retinal vein occlusion (RVO), and retinal artery occlusion (RAO). Among these diseases, AMD and DR are the major causes of progressive vision loss, while the latter is recognized as a world-wide epidemic. Advances in retinal imaging have improved the diagnosis and management of DR and AMD. In this review article, we focus on the variable imaging modalities for accurate diagnosis, early detection, and staging of both AMD and DR. In addition, the role of artificial intelligence (AI) in providing automated detection, diagnosis, and staging of these diseases will be surveyed. Furthermore, current works are summarized and discussed. Finally, projected future trends are outlined. The work done on this survey indicates the effective role of AI in the early detection, diagnosis, and staging of DR and/or AMD. In the future, more AI solutions will be presented that hold promise for clinical applications.

Keywords: artificial intelligence; diabetic retinopathy; macular degeneration; modalities; retinal diseases.

Figure 1

Common retinal diseases.

Figure 2

Analysis of retinal images.

Figure 3

Medical image modalities for the detection, diagnosis, and staging of DR and AMD.

Figure 4

Components of artificial intelligence (AI).

Figure 5

Summary of traditional ML methods for DR detection, diagnosis, and/or staging.

Figure 6

Summary of deep learning methods for DR detection, diagnosis, and/or staging.

Figure 7

Summary of traditional ML methods for AMD detection, diagnosis, and/or staging.

Figure 8

Summary of deep learning methods for AMD detection, diagnosis, and/or staging.