Diabetic Retinopathy Detection Using Artificial Neural Network

Rohini M.¹ , Gokila M.² , Nanthini N.³ , Pavithra M.⁴ , Ruth Lovelyn M.⁵

Section:Research Paper, Product Type: Journal-Paper
Vol.8 , Issue.4 , pp.116-121, Aug-2020

Online published on Aug 31, 2020

Copyright © Rohini M., Gokila M., Nanthini N., Pavithra M., Ruth Lovelyn M. . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
Diabetic retinopathy is a one type of eye disease which affect the people with diabetics. Diabetics mellitus commonly referred to as diabetics is a group of metabolic disorder in which there a high blood sugar level over prolonged period. It creates eye disease if left untreated. It causes many complications and one such complications is blindness. The high blood sugar level causes damage to blood vessels in retina that many are not aware of. There are three main phases namely preprocessing, segmentation, classification. The proposed model is implemented in MATLAB and the results are analyzed based on certain parameters. Preprocessing is done by median filter to remove unwanted noise and preserve the edges. From the input image the blood vessels are isolated and used in identifying the presence of microneurysms and exhudates. The blood vessels of the image are detected using morphological operation. Detecting the disease at an earlier stage can prevent the patients from vision loss. In this work ANN approach is used for better classification of diabetics and the classified images can be categorized under the stages of various abnormalities associated with eye

Key-Words / Index Term :
Artificial Neural Network, Segmentation, Feature Extraction

References :
[1] Wen Cao*, Juan Shan, Nicholas Czarnek, ?Microaneurysm Detection in Fundus Images Using Small Image Patches and Machine Learning Methods,? in 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
[2] Ravi Kamble, Manesh Kokare, ?DETECTION OF MICROANEURYSM USING LOCAL RANK TRANSFORM IN COLO FUNDUS IMAGES,? in IEEE International Conference on Image Processing (ICIP) 2017.
[3] I.S.Hephzi Punithavathi, Dr.P.Ganesh Kumar, ?Severity Grading of Diabetic Retinopathy Using Extreme Learning Machine? ,in IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT TECHNIQUES IN CONTROL, OPTIMIZATION AND SIGNAL PROCESSING 2017.
[4] J. Shan and L. Li, ?A Deep Learning Method for Microaneurysm Detection in Fundus Images,? in IEEE 1st InternationalConferenceon Connected Health: Applications, Systems and Engineering Technologies,CHASE 2016, 2016.
[5] Valliappan Raman, Patrick Then, Putra Sumari, Proposed Retinal Abnormality Detection and Classification Approach Computer Aided Detection for Diabetic Retinopathy by Machine Learning Approaches in 8th IEEE International Conference on Communication Software and Networks 2016 .
[6] May Phu Paing*, Somsak Choomchuay**, Rapeeporn Yodprom, MD, ?Detection of Lesions and Classification of Diabetic Retinopathy Using Fundus Images?, The 2016 Biomedical Engineering International Conference (BMEiCON-2016).
[7] A.Rajan, ?Detection of Diabetic Retinopathy in Fundus Image,? in International Journal of Science and Application, 2015,
[8] Shah Syed Ayaz Ali , Tong Boon Tang ,* Augustinus Laude and Ibrahima Faye, ?Making every Microaneurysm Count: A Hybrid Approach to Monitor Progression of DiabeticRetinopathy in 5th International Conference on Intelligent and Advanced Systems (ICIAS) 20149] M. Usman Akram et al., ?Detection and classification of retinal lesions for grading of diabetic retinopathy,? Comput. Biol. Med., vol. 45, no. 1,pp. 161?171, 2014
[9] M. UsmanAkram a,n, ShehzadKhalid b, AnamTariq a, ShoabA.Khan a, FarooqueAzam a, ?Detection and classification of retinal lesions for grading of diabetic retinopathy?,inComputersinBiologyandMedicine45(2014)16[1?171 2013.
[10] Meindert Niemeijer*, Bram van Ginneken, Member, IEEE, Michael J. Cree, Senior Member, IEEEAtsushi Mizutani, Gw?nol? Quellec, Clara I. S?nchez, Member, IEEE, Bob Zhang, ?Retinopathy Online Challenge: AutomaticDetection of Microaneurysms in Digital Color Fundus Photographs in IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 29, NO. 1, JANUARY 2010
[11] T. Kauppi et al., ?DIARETDB1 diabetic retinopathy database and evaluation protocol,? Proceedings Br. Mach. Vis. Conf. 2007, vol. 1, p.15.1-15.10, 2007.
[12] K. Ram, G. D. Joshi, and J. Sivaswamy, ?A successive clutter-rejection based approach for early detection of diabetic retinopathy,? IEEE Trans .Biomed. Eng., vol. 58, no. 3, pp. 664?673, 2011
[13]Harry pratt, Frans Coenen.B, ?Convolution neural network for Diabetic Retinopathy?, in international conference on medical imaging understanding and analysis 2016.
[14] Sean H.F and Han C.W .Haiso ? fast Detection of Microaneurysm Colour Fundus Image?, in IEEE 2nd International conference on Multimedia big data.
[15] Santhakumar R, Megha Tandur, E R Rajkumar ,Geetha K S,Girish Haritz, Kumar Thirunellai Rajamani, ?Machine Learning Algorithm for Retinal Image Analysis?, in IEEE Region 10 Conference (TENCON) 2016.