A Study on Recent Developments for Detection of Neovascularization

Abstract

Diabetes and its complications are major causes of death in most countries. One of the complications of diabetes is diabetic retinopathy, the disruption of vision because of the damage to the retinal blood vessels. Automatic screening of diabetic retinopathy is needed because of the increasing number of diabetic retinopathy patients and the limited number of ophthalmologists. Neovascularization (new abnormal blood vessel) is an indicator of proliferative diabetic retinopathy, which is the most advanced stage of diabetic retinopathy. The accurate detection of neovascularization is an important step for the early detection of proliferative diabetic retinopathy. This paper examines some of the current techniques used to detect neovascularization from retinal digital fundus images. Various algorithms include preprocessing steps, and image databases are discussed. This work can be used by researchers to conduct further research in the field of neovascularization detection.