An Automated Tracking Approach for Extraction of Retinal Vasculature in Fundus Images

Purpose: to present a novel automated method for tracking and detection of retinalblood vessels in fundus images.methods: for every pixel in retinal images, a feature vector was computed utilizingmultiscale analysis based on gabor filters. to classify the pixels based on their extractedfeatures as vascular or non-vascular, various classifiers including quadratic gaussian(qg), k-nearest neighbors (knn), and neural networks (nn) were investigated.the accuracy of classifiers was evaluated using receiver operating characteristic(roc) curve analysis in addition to sensitivity and specificity measurements. weopted for an nn model due to its superior performance in classification of retinalpixels as vascular and non-vascular.results: the proposed method achieved an overall accuracy of 96.9%, sensitivityof 96.8%, and specificity of 97.3% for identification of retinal blood vessels using adataset of 40 images. the area under the roc curve reached a value of 0.967.conclusion: automated tracking and identification of retinal blood vessels basedon gabor filters and neural network classifiers seems highly successful. througha comprehensive optimization process of operational parameters, our proposedscheme does not require any user intervention and has consistent performance forboth normal and abnormal images.