Diabetic Retinopathy Classification Using Machine Learning Techniques
 |
International Journal of Engineering Trends and Technology (IJETT) |  |
| © 2020 by IJETT Journal | ||
| Volume-68 Issue-1 |
||
| Year of Publication : 2020 | ||
| Authors : S. Regina Lourdhu Suganthi, U K Sneha, Shwetha S |
||
| DOI : 10.14445/22315381/IJETT-V68I1P207 |
Citation
MLA Style: S. Regina Lourdhu Suganthi, U K Sneha, Shwetha S "Diabetic Retinopathy Classification Using Machine Learning Techniques" International Journal of Engineering Trends and Technology 68.1 (2020):51-56.
APA Style:S. Regina Lourdhu Suganthi, U K Sneha, Shwetha S. Diabetic Retinopathy Classification Using Machine Learning Techniques International Journal of Engineering Trends and Technology, 68(1),51-56.
Abstract
Diabetic Retinopathy is an eye disease which is caused due to long term diabetes. It is one of the major complications of diabetes that affects the blood vessels by causing damage to the light-sensitive tissue. The working age population is largely affected by this disease. At first diabetic retinopathy may cause no symptoms at all. But eventually, it can result in blindness. Ophthalmology is a branch of medicine and surgery that deals with the diagnosis and treatment of eye disorders. The Ophthalmologists use the eye images of the patients to detect and advise preventive care for eye disorders. Using fundus camera the patient’s eye image is acquired as these Eye images are the primary data source for the classification. The images in its original form may not reveal the necessary features that are used for the purpose of classification. Thus, to apply machine learning algorithms, various attributes from the eye image are extracted using the domain knowledge to reveal different characteristics of the disease pattern. Automatic classification using machine learning techniques are generally rigid. Deep learning technique has been used for automatic classification and prediction with high accuracy. The pre-processed eye image data set is used to train the classifier for binary classification to infer the patient’s eye as an infected eye or a normal eye. The model has been evaluated using various measures namely, Precision, Recall, and F-Score. The severity of the disease is measured and classified into different categories using machine learning algorithms.
Reference
[1] Jiri Minar, Kamil Riha, Ales Krupka, Hejun Tong, “Automatic detection of the macula in retinal fundus images using multilevel thresholding”
[2] A. Biran, P. Sobhe Bidari, K Raahemifar, “Automatic method for Exudates and Hemorrhages detection from Fundus Retinal Images”, International Journal of Computer and Information engineering, Vol. 10, No.9, 2016.
[3] Wuttichai Luangruangrong, Pusit Kulkasem, Suwanna Rasmequan, Annupan Rodtook, Krisana Chinnasarn, “Automatic exudates detection in retinal images using efficient integrated approaches”, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014. Pgs 1-5.
[4] International Journal of Computer Applications (0975 – 8887) Volume 107 – No 12, December 2014
[5] Detection of Haemorrhage from Retinal Images Using Digital Image Processing Techniques. 2017 IJEDR | Volume 5, Issue 4 | ISSN: 2321-9939
[6] Automatic Optic Disc Detection in Color Retinal Images by Local Feature Spectrum Analysis. Hindawi ,Computational and Mathematical Methods in Medicine Volume 2018, Article ID 1942582, 12 pages
[7] S Regina Lourdhu Suganthi, M Hanumanthappa, S Kavitha, “Event Image Classification using Deep Learning”, IEEE, International Conference on Soft-computing and Network Security (ICSNS), 2018
[8] Ioffe, Sergey, and Christian Szegedy. "Batch normalization: Accelerating deep network training by reducing internal covariate shift ." arXiv preprint arXiv:1502.03167 (2015).
[9] Simonyan, K. and Zisserman, A, “Very deep convolutional networks for large-scale image recognition”, Proceedings of International Conference on Learning Representations. http://arxiv.org/abs/1409.1556 (2014).
Keywords
Decision Tree classifier, Random Forest, Support Vector Machine, Deep Learning, CNN, Diabetic Retinopathy, Machine Learning, ROI