Abstract
Automated detection of vision threatening eye disease based on high resolution retinal fundus images requires accurate segmentation of the blood vessels. In this regard, detection and segmentation of finer vessels, which are obscured by a considerable degree of noise and poor illumination, is particularly challenging. These noises include (systematic) additive noise and multiplicative (speckle) noise, which arise due to various practical limitations of the fundus imaging systems. To address this inherent issue, we present an efficient unsupervised vessel segmentation strategy as a step towards accurate classification of eye diseases from the noisy fundus images. To that end, an ensemble block matching 3D (BM3D) speckle filter is proposed for removal of unwanted noise leading to improved detection. The BM3D-speckle filter, despite its ability to recover finer details (i.e., vessels in fundus images), yields a pattern of checkerboard artifacts in the aftermath of multiplicative (speckle) noise removal. These artifacts are generally ignored in the case of satellite images; however, in the case of fundus images, these artifacts have a degenerating effect on the segmentation or detection of fine vessels. To counter that, an ensemble of BM3D-speckle filter is proposed to suppress these artifacts while further sharpening the recovered vessels. This is subsequently used to devise an improved unsupervised segmentation strategy that can detect fine vessels even in the presence of dominant noise and yields an overall much improved accuracy. Testing was carried out on three publicly available databases namely Structured Analysis of the Retina (STARE), Digital Retinal Images for Vessel Extraction (DRIVE) and CHASE_DB1. We have achieved a sensitivity of 82.88, 81.41 and 82.03 on DRIVE, SATARE, and CHASE_DB1, respectively. The accuracy is also boosted to 95.41, 95.70 and 95.61 on DRIVE, SATARE, and CHASE_DB1, respectively. The performance of the proposed methods on images with pathologies was observed to be more convincing than the performance of similar state-of-the-art methods.
Highlights
We propose an enhanced framework for computerized identification of eye diseases from retinal fundus images by employing S-block matching 3D (BM3D) denoiser in combination with unsupervised methods for detecting retinal vessels
Fundus images are severely affected by speckle noise due to scattering of the reflected light that distorts or conceals smaller vessels. These smaller vessels are not detected during segmentation. To address this issue we suggest the use of the state-of-the-art Speckle Adapted Block Matching 3D (S-BM3D) filter that can minimize speckle without compromising on the finer details
The input images are taken from the DRIONS dataset of noisy fundus images [74]
Summary
Analysis of biomedical images is one of the growing research fields. Rapid progress in the research domain of biomedical image processing has proven significantly important as it reduces the use of invasive approaches for diagnosis purposes. This research is based on the analysis of retinal fundus images for the diagnosis of eye disease using computerized techniques. The retina is present in the interior surface of the eye, which possesses photoreceptors that are the cells sensitive to light. They convert light into neural signals that are taken to the brain via optic nerves. The retinal image comprises important diagnostic information that helps to identify healthy or unhealthy retina. Retinal blood vessels can be used to diagnose different eye diseases as well as other diseases like diabetic retinopathy, glaucoma, and hypertension
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
