Comparative Analysis of Vessel Segmentation Techniques in Retinal Images

Yan Pei,Jianqiang Li,Qing Wang,Azhar Imran,Ji-Jiang Yang

doi:10.1109/access.2019.2935912

Abstract

The blood vessels are the primary anatomical structure that can be visible in retinal images. The segmentation of retinal blood vessels has been accepted worldwide for the diagnosis of both cardiovascular (CVD) and retinal diseases. Thus, it requires an appropriate vessel segmentation method for automatic detection of retinal diseases such as diabetic retinopathy and cataract. The detection of retinal diseases using computer-aided diagnosis (CAD) can help people to avoid the risks of visual impairment and save medical resources. This survey presents a comparative analysis of various machine learning and deep learning-based methods for automated blood vessel segmentation in retinal images. This paper briefly describes fundus photography, publicly available retinal databases, pre-processing and post-processing techniques for retinal vessels segmentation. A comprehensive review of the state of the art supervised and unsupervised blood vessel segmentation methodologies are presented in this paper. The objective of this study is to establish a professional structure to familiarize an individual with up-to-date vessel segmentation techniques. Moreover, we compared these approaches to the dataset, evaluation metrics, pre-processing and post-processing steps, feature extraction, segmentation methods, and induced results.

Highlights

The deep-rooted blood vessel of the eye can only be observed in a non-invasive manner is through the retina
The method achieved an accuracy of 0.918 and area under the curve (AUC) of 0.967 for retinal vessel segmentation task evaluated on publicly available retinal database Digital Retinal Images for Vessel Extraction (DRIVE)
The proposed method was evaluated on DRIVE dataset and has achieved state of the art accuracy comparing with others

Summary

Introduction

The deep-rooted blood vessel of the eye can only be observed in a non-invasive manner is through the retina. Retinal blood vessels are a main anatomical structure that can be detectable in the retinal fundus image. The structure and feature variations reflect the impact of CVD such as cataract, diabetic retinopathy (DR), and hypertension, etc. Diagnosis and cure of the cataract can avoid serious effects including blindness. A cataract is a thick, overcast zone that structures in the lens of the eye. A cataract starts when proteins in the eye shape bunches that retain the lens from sending clear pictures to the retina. A cataract is majorly categorized into three types based on the location of the retina where it develops i.e

Objectives

Methods

Findings

Discussion

Conclusion