Diabetic Retinopathy Diagnosis based on Deep Learning with Percolation Theory

Diabetic retinopathy is a disease of the retina that occurs in diabetic people and the main cause of blindness worldwide is diabetic retinopathy. For this reason, early diagnosis and treatment is necessary to delay or prevent vision loss or blindness. In this regard, many methods based on artificial intelligence have been proposed by the research community to diagnose and classify diabetic retinopathy on retinal fundus images. This approach have four level. In first level, pre-processing done for probabilistic noise removal and standardization of input dataset. Then Spiking Neural Network (SNN) done for image segmentation based on edge detection. In the following step, dimension reduction, feature selection and extraction done by percolation theory which features are blood vessels edges and intensity of edges. At the end, combination method of SNN and percolation theory done for detection the area of retinopathy. Results show that proposed method have the better accuracy in comparison to others.

Keywords:

Retinopathy , Image Segmentation , Edge Detection , Spiking Neural Network (SNN) , Percolation Theory