International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020


IJSTR >> Volume 9 - Issue 4, April 2020 Edition

International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616

Automatic Abnormal Structures Localization From Diabetic Retinopathy Images Using Differences In Intensity Values

[Full Text]



Raad Alwan



Diabetic Retinopathy, fundus image, intensity value, exudate, hemorrhage, cotton wool.



Diabetic patients require annual screening to prevent the infectious of Diabetic Retinopathy (DR) which cause blindness in the working ages. The dramatic dissemination of this disease all over the world turns the process of diagnosing and monitoring DR lesions to be time and effort consuming and the need to design an automatic system that has the ability to localize DR lesions and specify their type is indispensable. This paper presents a new technique that automatically localize all three DR lesions, exudates, hemorrhage and cotton wool by emphasizing the differences in intensity values of these lesions. Removing the optic disk is a preprocessing step to remove the effect of its intensity value on other structures; followed by highlighting each lesion type through consequent steps; and ending with localizing the lesions distinguishably. After intensive testing through five different datasets with more than 1500 images, the proposed technique achieved 98.99, 99.3, and 89.44 for accuracy, sensitivity, and specificity, respectively, which makes it to be competitive among several proposals.



[1] Taylor, H.R. and J.E. Keeffe, World blindness: a 21st century perspective. British Journal of Ophthalmology, 2001. 85(3): p. 261-266.
[2] Narasimha-Iyer, H., et al., Robust detectionand classification of longitudinal changes in color retinal fundus images formonitoring diabetic retinopathy. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006. 53(6): p. 1084-1098.
[3] A.P.Shingade and A.R.Kasetwar, A REVIEW ON IMPLEMENTATION OF ALGORITHMS FOR DETECTION OF DIABETIC RETINOPATHY. International Journal of Research in Engineering and Technology, 2014. 3(3).
[4] Xiao, D. and Y. Kanagasingam, Screening of the Retina in Diabetes Patients by Morphological Means, in Teleophthalmology in Preventive Medicine, M. G., Editor 2015, Springer, Berlin, Heidelberg. p. 15-26.
[5] Sinthanayothin, C., et al., Automated detection of diabetic retinopathy on digital fundus images. Diabetic Medicine, 2002. 19(1): p. 105-112.
[6] Walter, T., et al., A Contribution of Image Processing to the Diagnosis of Diabetic Retinopathy-Detection of Exudates in Color Fundus Images of the Human Retina. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2002. 21(10).
[7] Usher, D., et al., Automated detection of diabetic retinopathy in digital retinal images: a tool for diabetic retinopathy screening. Diabetic Medicine, 2003. 21(1): p. 84-90.
[8] Sopharak, A., et al., Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Computerized Medical Imaging and Graphics 2008. 32(2008): p. 720-727.
[9] JayaKumari, C. and R. Maruthi, Detection of Hard Exudates in Color Fundus Images of the Human Retina. Procedia Engineering, 2012. 30: p. 297-302.
[10] Usman Akram, M., et al., Detection and classification of retinal lesions for grading of diabetic retinopathy. Computers in Biology and Medicine, 2014. 45(2014): p. 161-171.
[11] Imani, E., H.-R. Pourreza, and T. Banaee, Fully automated diabetic retinopathy screening using morphological component analysis. Computerized Medical Imaging and Graphics, 2015. 43(2015): p. 78-88.
[12] Kumar, P.N.S., et al., Automated Detection System for Diabetic Retinopathy Using Two Field Fundus Photography. Procedia Computer Science, 2016. 93: p. 486-494.
[13] Pratt, H., et al., Convolutional Neural Networks for Diabetic Retinopathy. Procedia Computer Science, 2016. 90(2016): p. 200-205.
[14] Amin, J., et al., A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions. Journal of Computational Science, 2017. 19: p. 153-164.
[15] Qu, M., et al., Automatic diabetic retinopathy diagnosis using adjustable ophthalmoscope and multi-scale line operator. Pervasive and Mobile Computing, 2017.
[16] Al-Hamadani, B.T., A fast template-based technique to extract optic disc from coloured fundus images based on histogram features. International Journal of Signal and Imaging Systems Engineering 2018. 11(2): p. 117-127.
[17] AL-HAMADANI, B.T., LOCALIZING MULTIPLE SCLEROSIS LESIONS FROM T2W MRI BY UTILIZING IMAGE HISTOGRAM FEATURES. Journal of Theoretical and Applied Information Technology, 2019. 97(17): p. 4547-4564.
[18] Decencière, E., et al., FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE. Image Analysis & Stereology, 2014. 33(3): p. 231-234.
[19] Staal, J.J., et al., Ridge based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging, 2004. 23: p. 501-509.
[20] University, C. STARE Project Website Clemson. 2003 2013; Available from: http://cecas.clemson.edu/~ahoover/stare/.
[21] Kauppi, T., et al., DIARETDB0: Evaluation Database and Methodology for Diabetic Retinopathy Algorithms, 2006: Technical Report.
[22] Kauppi, T., et al. Diaretdb1 diabetic retinopathy database and evaluation protocol. in Medical Image Understanding and Analysis (MIUA). 2007.