A region growing and local adaptive thresholding-based optic disc detection.

Tariq M Khan,Mehwish Mehmood,Muhammad Fasih Uddin Butt,Syed S Naqvi

doi:10.1371/journal.pone.0227566

Abstract

Automatic optic disc (OD) localization and segmentation is not a simple process as the OD appearance and size may significantly vary from person to person. This paper presents a novel approach for OD localization and segmentation which is fast as well as robust. In the proposed method, the image is first enhanced by de-hazing and then cropped around the OD region. The cropped image is converted to HSV domain and then V channel is used for OD detection. The vessels are extracted from the Green channel in the cropped region by multi-scale line detector and then removed by the Laplace Transform. Local adaptive thresholding and region growing are applied for binarization. Furthermore, two region properties, eccentricity, and area are then used to detect the true OD region. Finally, ellipse fitting is used to fill the region. Several datasets are used for testing the proposed method. Test results show that the accuracy and sensitivity of the proposed method are much higher than the existing state-of-the-art methods.

Highlights

Some eye diseases such as diabetic retinopathy (DR) require an automatic system to screen a large number of patients at regular intervals
Several research efforts have been made in the past that deal with detecting retinal parts like an optic disc (OD), blood vessels, field of view (FOV) and retinal lesions containing exudates, microaneurysms, and hemorrhages [[1]–[2]]
This paper presents an algorithm for OD localization and OD detection which has been verified using six databases: DIARETDB1, MESSIDOR, DRIONS, DRISHTI, RIM-ONE and ONHSD

Summary

Introduction

Some eye diseases such as diabetic retinopathy (DR) require an automatic system to screen a large number of patients at regular intervals. Fundus image analysis is a challenging task as fundus images contain variable colors. The morphology of retinal structures and specific features in various patients may lead to incorrect diagnosis. Several research efforts have been made in the past that deal with detecting retinal parts like an optic disc (OD), blood vessels, field of view (FOV) and retinal lesions containing exudates, microaneurysms, and hemorrhages [[1]–[2]]. Retinal vasculature can be damaged due to eye-related diseases such as DR which is a common diabetic disease and a leading cause of blindness. The retina of the eye is badly affected when tiny blood vessels are damaged due to hypertension and high sugar level resulting in vision loss problems.

Objectives

Results

Conclusion