Retinal Based Disease Prediction using Deep Neural Networks and SVM Classification Techniques

  IJETT-book-cover  International Journal of Engineering Trends and Technology (IJETT)          
  
© 2017 by IJETT Journal
Volume-49 Number-7
Year of Publication : 2017
Authors : R.Hannah Roseline, R.Jemina Priyadarsini
  10.14445/22315381/IJETT-V49P268

MLA 

R.Hannah Roseline, R.Jemina Priyadarsini "Retinal Based Disease Prediction using Deep Neural Networks and SVM Classification Techniques", International Journal of Engineering Trends and Technology (IJETT), V49(7),437-444 July 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group

Abstract
In medical field, diagnosis of diseases is competently carried out with the help of image processing. So that the retrieval of the relevant data from the amalgamation of resulting image is a hard process. Human eye is an important organ that reacts to light and has several purposes. The eye is composed of a number of components which include but are not limited to the cornea, iris, pupil, lens, retina, macula, optic nerve, choroid and vitreous. The significant health issues among the senior individuals are eye ailments. Retina is said to be one of the most important internal component of the eye. Retinal images could be used in several applications that help in diagnosing the disease and human recognition. They also play a major role in early detection of diseases related to cardio vascular diseases by comparing the states of the retinal blood vessels. Retinal Image Analysis (RIA) is a key element in detecting diseases in patients. Applications of retinal images are diagnosing the progress of some cardiovascular diseases, diagnosing the region with no blood vessels (Macula).Retinal image analysis is a complicated task particularly because of the variability of the images in terms of the color, the morphology of the retinal anatomical structure and the existence of particular features in different patients, which may lead to an erroneous interpretation In this work we detect the blood vessels effectively by using deep Neural Networks (NN) for segmentation and Support Vector Machine (SVM) for classification and the diagnosis of disease such as stroke, heart attack and cardio vascular diseases. The experimental result shows a better accuracy in predicting the disease.

Reference
[1] Abdallah, Mariem Ben, et al. "Automatic extraction of blood vessels in the retinal vascular tree usin medialness." Journal of Biomedical Imaging
[2] Kaur, Manvir, and Rajneesh Talwar. "Automatic Extraction of Blood Vessel and Eye Retinopathy Detection." European Journal of Advances in Engineering and Technology 2.4 (2015): 57-61.
[3] Wang, Shuangling, et al. "Hierarchical retinal blood vessel segmentation based on feature and ensemble learning." Neurocomputing 149 (2015): 708
[4] Vidyashree, M. R., M. V. Usha, and the optic nerve and blood vessel in a re graph partition method." (2015).
[5] Annunziata, Roberto, et al. "Leveraging multiscale hessian-based enhancement with a novel exudate inpainting technique for retinal vessel segmentation." IEEE journal of biomedical and health informatics 20.4 (2016): 1129-1138.
[6] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014.
[7] Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle et al., “Greedy layer-wise training of deep networks,” Advances in neural information processing systems, vol. 19, p. 153, 2007.
[8] M. Fraz, P. Remagnino, A. Hoppe, B. Uyyanonvara, A. Rudnicka, C. Owen, and S. Barman, “Blood vessel segmentation methodologies in retinal images - a survey,” Comput. Methods Prog. Biomed. vol. 108, no. 1, pp. 407–433, Oct. 2012. [Online]. Available: http://dx.doi.org/10.1016/j.cmpb.2012.03.009.
[9] J. Staal, M. D. Abràmoff, M. Niemeijer, M. A. Viergever, and B. van Ginneken, “Ridge-based vessel segmentation in color images of the retina,” Medical Imaging, IEEE Transactions on, vol. 23, no. 4, pp. 501–509, 2004.
[10] A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,” Medical Imaging, IEEE Transactions on, vol. 19, no. 3, pp. 203–210, 2000.
[11] Poonam Bhosale,Pradnya Kulkarni,Sarika Bobde , “ Automatic detection of age related macular degeneration using retinal colour images”,Sixth Post Graduate Conference for Computer Engineering(cPGCON 2017) Procedia International Journal on Emerging Trends in Technology(IJETT).
[12]Rasika,P.Rahane,Deepak Gupta, “ Efficient Iris Recognition System using Robust Iris Segmentation and Hybrid Feature Extraction Methods”, Sixth Post Graduate Conference for Computer Engineering(cPGCON 2017) Procedia International Journal on Emerging Trends in Technology(IJETT).

Keywords
The experimental result shows a better accuracy in predicting the disease.