Retinal Blood Vessel Region Exploration by Hybrid Method Segmentation

Accurate segmentation and evaluation of the anatomical and pathological features of retinal vessels are critical for the diagnosis and study of many ocular diseases. These include retinopathy of prematurity (ROP). ROP is a disorder of the retinal blood vessels that is a major cause of vision loss in premature neonates. It is proposed a methodology for extracting the vascular network in the human retina using Hybrid automatic vessel segmentation method by using shortest path algorithm. In this method by preserving vessel thickness, without manual intervention, vessel branching is achieved naturally and efficiently. A single-frame image enhancement step can be optionally replaced by a multi-frame image mosaiking technique. This technique recently developed to combine several low Quality Video Indirect Ophthalmoscopes (VIO) frames into a high-quality, large field-of-view (FOV) composite [9]. As results this approach provides a superior segmentation results on both types of –raw and composite– VIO images compared to current state-of-the-art segmentation methods. Keywords—Image processing, Image analysis, Ophthalmology, Retinopathy