Robust Retinal Vessel Segmentation using Vessel's Location Map and Frangi Enhancement Filter

The analysis of retinal vascular is quite important because many diseases including stroke, diabetic retinopathy (DR) and coronary heart diseases can damage retinal vessel structure. In this research, a technique has been proposed using a combination of pre-processing steps, vessel enhancement techniques, segmentation and post-processing. The pre-processing section comprises of adaptive histogram equalisation for dissimilarity enhancement between vessels and background, a morphological top hat filter for macula and optic disc removal and high boost filtering, edges enhancement. Frangi filter is applied at multi-scale for enhancement of different vessel widths. Segmentation has been performed using global Otsu thresholding with some offset applied on difference image and enhanced image separately. A vessel location map (VLM) has been extracted using the post-processing steps of raster to vector transformed area and eccentricity-based threshold to eliminate the exudate/unwanted region from binarised image. Post-processing has been used in a new way to reject misclassified vessel pixels. The final segmented image has been obtained by using pixel-by-pixel AND operation between VLM and Frangi binarised image. The method has been rigorously analysed using STARE and DRIVE datasets.