A Method of Disease Detection and Segmentation of Retinal Blood Vessels using Fuzzy C-Means and Neutrosophic Approach

Diabetic Retinopathy is a disease which causes a menace to the eyesight. The detection of this at an early stage can aid the person from vision loss. The examination of retinal blood vessel structure can help to detect the disease, so segmentation of retinal blood vessel vasculature is important and is appreciated by the ophthalmologists. In this paper, we present the approach of blood vessel segmentation using computer intelligence by deploying fuzzy c-means and neutrosophic set. Further, the input image is scrutinized and the result achieved is whether the image is diseased or not. The various diseases detected in this technique are cotton wool spots, exudates and lesions with the help of region growing and neural network classification method. The proposed approach is tested on DRIVE and DIARETDB1 databases and is compared with the other approaches. The segmentation approach achieved the average accuracy of 98.7% whereas the diseased image was detected with 99% accuracy. Keywords— Diabetic Retinopathy, Retina, Blood vessels, Neutrosophy, Fundus Images, Segmentation .