Retinal Blood Vessel Segmentation from Depigmented Diabetic Retinopathy Images

Diabetic Retinopathy is a progressive disease that affects diabetic patients and changes the width and tortuosity of the retinal blood vessels. The preferred center of attention is to predict the new vessel growth and the dissimilarity in diameter of the retinal blood vessels. To examine the changes, primarily segmentation has to be made. A system has been proposed to enhance the quality of the segmentation result over pathological retinal images. The proposed system comprises preprocessing of Fundus images and extracts the blood vessels. The proposed system uses Contrast Limited Adaptive Histogram Equalization (CLAHE) for preprocessing and Tandem Pulse Coupled Neural Network (TPCNN) model to segment the retinal vasculature. To categorize the small blood vessels from pathological images, the algorithm depending on its parameters. In the former PCNN model, the parameters have to be set at every time for all images. The proposed TPCNN model assigns values for its multiple parameters through Particle Swarm Optimization (PSO); so that the decay speeds of the threshold would be regulated adaptively. This greatly enhances the flexibility of TPCNN in dealing with depigmented pathological images. The generated feature vectors of blood vessels are classified and extracted via Deep Learning Based Support Vector Machine (DLBSVM) technique. The proposed method is assessed over DRIVE, STARE, HRF, REVIEW, CHASE_DB1 and DRIONS databases by the performance parameters such as Sensitivity, Specificity, Accuracy, and Receiver Operating Characteristic (ROC) curve. The results render that these techniques improve the segmentation with an average value of 94.68% Sensitivity, 99.70% Specificity, 99.61% Accuracy and 98% ROC. The results evoke that the proposed methods are a suitable alternative for the supervised methods.