Unsupervised Method for Retinal Vessel Segmentation Based on Gabor Wavelet and Multiscale Line Detector

Syed Ayaz Ali Shah,Muhammad Amir Khan,Tong Boon Tang,Aamir Shahzad,Cheng-Kai Lu

doi:10.1109/access.2019.2954314

Abstract

Eye and systemic diseases are known to manifest themselves in retinal vasculature. Segmentation of retinal vessel is one of the important steps in retinal image analysis. A simple unsupervised method based on Gabor wavelet and Multiscale Line Detector is proposed for retinal vessel segmentation. Vessels are enhanced by linear superposition of first scale Gabor wavelet image and complemented Green channel. Multiscale Line Detector is used to segment the blood vessels. Finally, a simple post processing scheme based on median filtering is deployed to remove false positives. The proposed scheme was evaluated with publicly available datasets called DRIVE, STARE and HRF, obtaining an accuracy of 0.9470, 0.9472, and 0.9559, and a sensitivity of 0.7421, 0.8004, and 0.7207, respectively. These results are comparable to the state-of-the-art methods, albeit with a simpler approach.

Highlights

One of the important tasks in diagnosing different medical conditions such as diabetic retinopathy, cardiovascular diseases, and stroke is the segmentation of blood vessels in color medical images
Post-processing: After application of Multiscale Line Detector, there were false positives around the Region of Interest (ROI) boundary, in the optic disc (OD) region and at the edges of the medium and fine vessels. To remove these false positives, we proposed a postprocessing scheme in which background was calculated using a median filter of the size of 15 × 15, 17 × 17 and 45 × 45, respectively for DRIVE, STARE and High-Resolution Fundus (HRF) datasets and removed from the green channel
We achieved an accuracy of 0.9470, sensitivity of 0.7421, false positive rate of 0.0227, and Matthews Correlation Coefficient (MCC) of 0.7525 on DRIVE dataset

Summary

Introduction

One of the important tasks in diagnosing different medical conditions such as diabetic retinopathy, cardiovascular diseases, and stroke is the segmentation of blood vessels in color medical images. To this end, different strategies have been devised. The strategies can be roughly grouped into i) multiscale, ii) matched filtering, iii) mathematical morphology, iv) hierarchical, v) model and vi) deep learning approach [1]. They can be categorized into supervised and unsupervised algorithm. Examples of filter based approach are [6]–[8] and

Methods

Results

Conclusion