Abstract
Diabetic retinopathy (DR) is an important retinal disease threatening people with the long diabetic history. Blood leakage in retina leads to the formation of red lesions in retina the analysis of which is helpful in the determination of severity of disease. In this paper, a novel red-lesion extraction method is proposed. The new method firstly determines the boundary pixels of blood vessel and red lesions. Then, it determines the distinguishing features of boundary pixels of red-lesions to discriminate them from other boundary pixels. The main point utilized here is that a red lesion can be observed as significant intensity changes in almost all directions in the fundus image. This can be feasible through considering special neighborhood windows around the extracted boundary pixels. The performance of the proposed method has been evaluated for three different datasets including Diaretdb0, Diaretdb1 and Kaggle datasets. It is shown that the method is capable of providing the values of 0.87 and 0.88 for sensitivity and specificity of Diaretdb1, 0.89 and 0.9 for sensitivity and specificity of Diaretdb0, 0.82 and 0.9 for sensitivity and specificity of Kaggle. Also, the proposed method has a time-efficient performance in the red-lesion extraction process.
Highlights
Literature reviewA number of most important research works which are related to the field of abnormality detection in retinal fundus images are reviewed
Diabetic retinopathy (DR) is an important retinal disease threatening people with the long diabetic history
In order to determine the values of the proposed algorithm (TP), true negative (TN), false positive spot (FP) and false negative (FN), after extracting the boundary pixels related to red-lesions, it is verified whether or not they are included inside a red-lesion localized and annotated by the ophthalmologist in the dataset
Summary
A number of most important research works which are related to the field of abnormality detection in retinal fundus images are reviewed. In Ref.[31] a method is proposed for vessel segmentation in retinal fundus images which works based on local adaptive thresholding. In Ref.[37] a method is proposed to find and fill the exudates in the retinal fundus images so that false positive regions are reduced and vessel segmentation is enhanced. In Ref.[38] a method for automated MA detection in retinal fundus images is proposed which consists of pre-processing, candidate extraction, feature extraction and classification phases. A method for detecting and classifying abnormalities in retinal fundus images is presented in Ref.[41] In this method a blob-ness measure is proposed and several intensity and shape features are utilized to identify DR related changes. The experimental results show that the proposed method has an improved performance in terms of speed and accuracy in comparison with the related state-of-the-art research works
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.
