Proliferative Diabetic Retinopathy Detection Using Machine Learning
DOI:
https://doi.org/10.26438/ijcse/v8i6.106111Keywords:
Feature Extraction, K-means clustering, morphological image processing, Neovascularization, Support vector machineAbstract
In this paper, the method for detection of neovascularization from fundus retinal image is presented. Neovascularization is the type of proliferative diabetic retinopathy and it is characterized by new, fragile retina vessels. It poses high risk for sudden vision loss. To avoid this risky situation, an early detection, proper treatment and diagnosis is essential. Therefore, we cannot underestimate the significance of accurate and timely detection of NV. We propose a method to detect NV which is based on automatic image processing that involves vessel segmentation using K-means, Vessel morphology, texture based features extraction and classification of images with support vector machine(SVM) and we achieved an average accuracy of 99 % on the selected test set.
References
[1] M. D. Abr?amoff, M. K. Garvin, and M. Sonka, ?Retinal imaging and picture analysis,? IEEE Reviews in Medicine Engineering, vol. 3, pp. 169?208, 2010.
[2] K. A. Goatman, A. D. Fleming, S. Philip, G. J. Williams, J. A. Olson, and P. F. Clear, ?New color fundus picture detection vessels?? IEEE transactions on medical imaging, vol. 30, no. 4, pp. 972?9, 2011.
[3] R. Welikala, M. Fraz, J. Dehmeshki, A. Hoppe, V. Tah, S. Mann, T. Williamson, and S. Barman, ?Genetic algorithmic program primarily based on various features combined with two classification for the machine driven detection of proliferative diabetic retinopathy,?processed Medical Imaging and Graphics, vol. 43, pp.64-77, 2015.
[4] R. Welikala, J. Dehmeshki, A. Hoppe, V. Tah, S. Mann, T. Williamson,and S. Barman, ?Automated detection and dual classification of the proliferative diabetic retinopathy? Computer Methods and programs in biomedicine, vol. 114, no. 3, pp. 247-261,2014
[5] S. S. A. Hassan, D. B. L. Bong, and M. Premsenthil, ?Detection of Neovascularization in Diabetic Retinopathy,? Journal of Digital maging, vol. 25, no. 3, pp. 437?444, 2012.
[6] C. Agurto, H. Yu, V. Murray, M. S. Pattichis, S. Barriga, W. Bauman, and P. Soliz, ?Detection of neovascularization at intervals the optic disc follow associate AM-FM illustration, granulometry, and vessel segmentation?, Annual International Conference of the IEEE Engineering in and Biology Society, vol.2012, pp. 4946-9,2012.
[7] Q. Li, ?Neovascularity detection based upon fractal analysis and texture analysis with diabetic retinopathy interaction effects,? PLoS ONE, vol. 8, no. 12, 2013.
[8] S. Eswari and S. Rajeswari, ?Recent vessels detection method in retinal fundus images A Survey,? in In Computing Technologies and Intelligent Data Engineering (ICCTIDE), International Conference on, pp. 1?6, 2016.
[9] K. Saranya, B. Ramasubramanian, and S. Kaja Mohideen, ?A novel approach for the detection of new vessels in the retinal images for screening Diabetic Retinopathy,? 2012 International Conference on Communication and Signal Processing, pp. 57?61, 2012.
[10] S. D. Kasurde and S.N.Randive, ?An Automatic Detection of Proliferative Diabetic Retinopathy,? in Energy Systems and Applications, 2015 International Conference on, pp. 86?90, 2015.
[11] B. Ramasubramanian and G. Anitha, ? An Effective Approach to Detect New Vessels in Diabetic Retinopathy images,? International Journal of Engineering and Innovative Technology(IJEIT), vol. 2, no. 3, pp. 240-244, 2012.
[12] G. Gupta, S. Kulasekaran, K. Ram, M. Sivaprakasam, M. N. Joshi and R. Gandhi, ?Local Neovascularization Characterisation and Identification of retinal retinopathy in proliferative diabetic fundus Images, ?Medical Imaging and Graphics Computerised, vol. 55, 55 Pp. 132? 124, 2017.
[13] ?Automatic Neovascularization Identification of Optic Disc Region based on Machine Learning? IEEE Transaction.
[14] N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, 2000.
[15] T. Kauppi, V. Kalesnykiene, J.-k. Kamarainen, L. Lensu, and I. Sorri, ?DIARETDB0 : Evaluation Database and Methodology for Diabetic Retinopathy Algorithms,? Machine Vision and Pattern Recognition Research Group, Lappeenranta University of Technology, Finland.,pp. 1?17, 2006.
[16] David A. Clausi, ?An analysis of the co-occurrence texture statistics based on gray levels?, Can. J. Remote Sensing, vol. 28, no. 1, pp. 45-62, 2002.
[17] M.S.Miri, and A. Mahloojifar ?A Review of Contrast to Determine Retinal Image Enhancement Techniques ?ICSIPA (2009) 90 ? 94.
[18] M.Rajesh Babu, BVNR Siva Kumar. Morphological process and SVM classification of diabetic retinopathy diagnosis. September 2016 , IJIRT ,Volume 3 Issue 4 ,ISSN: 2349- 6002.
[19] J.A. Hartigan and M.A. Wong, ?Algorithm AS 136: A algorithm of k-means clustering ,? Applied Statistics, vol. 28, pp. 100-108, 1979.
[20] Kaggle,?Diabetic Retinopathy Detection Challenge.?https://www.kaggle.com/c/diabetic-retinopathydetection. Accessed: 2016-07-05.
[21] Vijay Kumar, Priyanka Gupta, ?Importance of Statistical Measures in Digital Image Processing,? International Journal of Emerging Technology and Advanced Engineering, ISBN: 22502459, vol. 2(8), August 2012.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
