Diabetic retinopathy screening using retinal blood vessel and lesions segmentation: A comparative study

Diabetes is a disease that reduces the human body's ability to store and regulate sugar. This disease develops due to excessive intake of food with higher sugar, excessive work pressure or unbalanced routines lacking in proper diet. Diabetes once developed is then harder to overcome and thus effects the human body functioning leading to failure of many human body parts. One of the major problem associated with the diabetes is vision loss, technically called Diabetic Retinopathy (DR). Analyzing retinal images via automation is evolving and proving its importance in screening of early detection of diabetic retinopathy. The early detection of DR is helpful in overcoming the disease preventing blindness. Many researches have been carried out in the past years for the development of automated tools that could help simplify screening of effected images and reduce evaluation time in detection of disease. This work is aimed at studying the algorithms for detection as well as classification of diabetic retinopathy and presenting a brief summary of selective relevant work amongst the methods being proposed in last 5 years till date. A comparative study of latest techniques that provides the best results for the screening of diabetic retinopathy through the analysis and segmentation of lesions is presented.