Analysis Of Ophthalmic Disorders For Retinal Images Using Deep Learning: A Review

Main Article Content

R.S.Latha ,G.R.Sreekanth, B.Bizu, K.Suvalakshmi, R.Esakki Selvaraj

Abstract

A summary of deep learning applications for ophthalmic disorders for retinal fundus images is given. Retinal Detachment, Macular Bunker, Retinoblastoma, Diabetic Retinopathy (DR), Age-Related Macular Degeneration (AMD), and Retinitis Pigmentosa are only a few of the retinal diseases that can be detected and categorized using retinal image analysis. Automated retinal disease detection is a major measure toward prior analysis and avoidance of disease exacerbation. Several state-of-the-art methods for automated segmentation and recognition of retinal landmarks and pathologies have been developed in the past. However, recent breakthroughs in deep learning and the contemporary imaging process in ophthalmology have opened up an entirely new world of possibilities for analysts. This paper is a study of deep learning techniques for automatic detection of diseases including age-related macular degeneration(AMD), glaucoma, diabetic retinopathy(DR), retinal landmarks, and anatomy using 2-D(two-dimension) fundus and 3-D (three dimensions) Optical Coherence Tomography (OCT) retinal images. The techniques are evaluated in terms of area under the ROC curve, sensitivity, accuracy, specificity, and F score.

Article Details

Section
Articles