Pattern RecognitionNo Access

Computer Aided Bright Lesion Classification in Fundus Image Based on Feature Extraction

Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, K L E F (K L Deemed to be University), Vaddeswaram, Guntur-522502, Andhra Pradesh, India

E-mail Address: bhargavi6464@kluniversity.in

Corresponding author.

Search for more papers by this author

and

V. Rajesh

Department of Electronics and Communication Engineering, Koneru Lakshmaiah Education Foundation, K L E F (K L Deemed to be University), Vaddeswaram, Guntur-522502, Andhra Pradesh, India

E-mail Address: rajesh71@kluniversity.in

Search for more papers by this author

https://doi.org/10.1142/S0218001418500349Cited by:7 (Source: Crossref)

Abstract

In this paper, a hybrid approach of fundus image classification for diabetic retinopathy (DR) lesions is proposed. Laplacian eigenmaps (LE), a nonlinear dimensionality reduction (NDR) technique is applied to a high-dimensional scale invariant feature transform (SIFT) representation of fundus image for lesion classification. The applied NDR technique gives a low-dimensional intrinsic feature vector for lesion classification in fundus images. The publicly available databases are used for demonstrating the implemented strategy. The performance of applied technique can be evaluated based on sensitivity, specificity and accuracy using Support vector classifier. Compared to other feature vectors, the implemented LE-based feature vector yielded better classification performance. The accuracy obtained is 96.6% for SIFT-LE-SVM.

Keywords:

References

1. M. D. Abr`amoff, J. M. Reinhardt, S. R. Russell, J. C. Folk, V. B. Mahajan, M. Niemeijer and G. Quellec , Automated early detection of diabetic retinopathy, Ophthalmology 117 (6) (2010) 1147–1154. Crossref, Web of Science, Google Scholar
2. C. Agurto, V. Murray, E. Barriga, S. Murillo, M. Pattichis, H. Davis, S. Russell, M. Abramoff and P. Soliz , Multiscale AM-FM methods for diabetic retinopathy lesion detection, IEEE Trans. Med. Imag. 29 (2) (2010) 502–512. Crossref, Web of Science, Google Scholar
3. M. Belkin and P. Niyogi , Laplacian eigenmaps for dimensionality reduction and data representation, Neural Comput. 15 (2003) 1373–1396. Crossref, Web of Science, Google Scholar
4. V. Caselles, F. Catte, T. Coll and F. Dibos , A geometric model for active contours in image processing, Numer. Math. 66 (1993) 1–31. Crossref, Web of Science, Google Scholar
5. E. Decenci`ere, G. Cazuguel, X. Zhang, G. Thibault, J.-C. Klein, F. Meyer, B. Marcotegui, G. Quellec, M. Lamard and R. Danno , Teleophta: Machine learning and image processing methods for teleophthalmology, Ing´enierie et Recherche Biom´edicale 34 (2013) 196–203. Google Scholar
6. K. Deepak and J. Sivaswamy , Automatic assessment of macular edema from color retinal images, IEEE Trans. Med. Imag. 31 (3) (2012) 766–776. Crossref, Web of Science, Google Scholar
7. E. Eisemann and F. Durand , Flash photography enhancement via intrinsic relighting, ACM Trans. Graph. 23 (3) (2004) 673–678. Crossref, Web of Science, Google Scholar
8. A. D. Fleming, K. A. Goatman, S. Philip, G. J. Prescott, P. F. Sharp and J. A. Olson , Automated grading for diabetic retinopathy: A large-scale audit using arbitration by clinical experts, Br. J. Ophthalmol. 94 (12) (2010) 1606–1610. Crossref, Web of Science, Google Scholar
9. L. Giancardo, F. Meriaudeau, T. P. Karnowski, Y. Li, S. Garge, K. W. Tobin and E. Chaumd , Exudate-based diabetic macular edema detection in fundus images using publicly available datasets, Med. Image Anal. 16 (2012) 216–226. Crossref, Web of Science, Google Scholar
10. H. Jelinek and M. Cree , Automated Image Detection of Retinal Pathology (CRC Press, Boca Raton, FL, USA, 2010). Google Scholar
11. H. Jelinek, R. Pires, R. Padilha, S. Goldenstein, J. Wainer and A. Rocha , Data fusion for multi-lesion diabetic retinopathy detection, in Proc. IEEE Comput.-Based Med. Syst. (2012), pp. 1–4. Google Scholar
12. M. Kass, A. Witkin and D. Terzopouls , Snake: Active contour models, Proc. Int. J. Computer Vis 1 (4) (1987) 321–331. Crossref, Web of Science, Google Scholar
13. T. Kauppi, V. Kalesnykiene, J.-K. Kmrinen, L. Lensu, I. Sorr, A. Raninen, R. Voutilainen, H. Uusitalo, H. Klviinen and J. Pietil , Diaretdb1 diabetic retinopathy database and evaluation protocol, in Proc. 11th Conf. Med. Image Understand. Anal. (2007), pp. 61–65. Google Scholar
14. S. Keshabparhi and D. D. Koozekanani , DREAM: Diabetic retinopathy analysis using machine learning, IEEE J. Biomed. Health Informatics 18 (5) (2014). Web of Science, Google Scholar
15. C. Li, C. Xu, C. Gui and M. D. Fox , Level set evolution without re-initialization: A new variational formulation, in Proc.IEEE Conference Computer Vision and Pattern Recognition (CVPR’05). Vol. 1, pp. 430–436. Google Scholar
16. J. Lie, M. Lysaker and X. C. Tai , A variant of the level set method and applications to image segmentation, Math. Comput. 75 (255) (2006) 1155–1174. Crossref, Web of Science, Google Scholar
17. D. G. Lowe , Object recognition from local scale invariant features, ICCV (1999), pp. 1150–1157. Google Scholar
18. Methods to evaluate segmentation and indexing techniques in the field of retinal ophthalmology. (2011, Sep. 23). [Online]. Available at http://messidor.crihan.fr/download-en.php. Google Scholar
19. M. R. K. Mookiah, U. Rajendra Acharya, R. J. Martis, C. K. Chua, C. M. Lim, E. Y. K. Ng and A. Laude , Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach, Knowl. Based Syst. 39 (2013) 9–22. Crossref, Web of Science, Google Scholar
20. J. Nayak, P. S. Bhat and U. R. Acharya , Automatic identification of diabetic maculopathy stages using fundus images, J. Med. Eng. Technol. 33 (2) (2009) 119–129. Crossref, Google Scholar
21. K. Noronha, U. R. Acharya, K. P. Nayak, S. Kamath and S. V. Bhandary , Decision support system for diabetic retinopathy using discrete wavelet transform, J. Eng. Med. 227 (3) (2012) 251–261. Google Scholar
22. S. Osher and R. Fedkiw , Level set methods: An overview and some recent results, J. Computer Phys. 169 (2001) 463–502. Crossref, Web of Science, Google Scholar
23. T. Peto and C. Tadros , Screening for diabetic retinopathy and diabetic macular edema in the United Kingdom, Curr. Diab. Rep. 12 (4) (2012) 338–345. Crossref, Web of Science, Google Scholar
24. G. Petschnigg, R. Szeliski, M. Agrawala, M. Cohen, H. Hoppe and K. Toyama , Digital photography with flash and no-flash image pairs, ACM Trans. Graph. 23 (3) (2004) 664–672. Crossref, Web of Science, Google Scholar
25. R. Pires, H. F. Jelinek, J. Wainer, S. G. Valle and A. Rocha , Assessing the need for referral in automatic diabetic retinopathy detection, IEEE Trans. Biomed. Eng. 60 (12) (2013) 3391–3398. Crossref, Web of Science, Google Scholar
26. R. Pires, H. F. Jelinek, J. Wainer and A. Rocha , Retinal image quality analysis for automatic diabetic retinopathy detection, in Proc. IEEE Conf. Graph., Patterns Images (SIBGRAPI) (2012), pp. 229–236. Google Scholar
27. A. Rocha, T. Carvalho, H. Jelinek, S. Goldenstein and J. Wainer , Points of interest and visual dictionaries for automatic retinal lesion detection, IEEE Trans. Biomed. Eng. 59 (8) (2012) 2244–2253. Crossref, Web of Science, Google Scholar
28. S. Roychowdhury, D. D. Koozekanani and K. K. Parhi , Screening fundus images for diabetic retinopathy, in Proc. Conf. Record 46th Asilomar Conf. Signals, Syst. Comput. (2012), pp. 1641–1645. Google Scholar
29. C. I. Sánchez, R. Hornero, M. I. López, M. Aboy, J. Poza and D. Abásolo , A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis, Med. Eng. Phys. 30 (3) (2009) 350–357. Crossref, Web of Science, Google Scholar
30. A. Sopharak, B. Uyyanonvara, S. Barman and T. H. Williamson , Automatic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods, Comput. Med. Imag.Graph. 32 (8) (2008) 720–727. Crossref, Web of Science, Google Scholar
31. G. Takacs, V. Chandrasekhar, D. Chen, S. Tsai, R. Grzeszczuk and B. Girod , Unified real-time tracking and recognition with rotation invariant fast features, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2010), pp. 934–941. Google Scholar
32. J. H. Tan, H. Fujita, S. Sivaprasad and U. Rajendra Acharya , Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network, Inform. Sci. 420 (2017) 66–76. Crossref, Web of Science, Google Scholar
33. J. H. Tan, U. R. Acharya, S. V. Bhandary, K. C. Chua and S. Sivaprasad , Segmentation of optic disc, fovea and retinal vasculature using a single convolutional neural network, J. Comput. Sci. 20 (2017) 70–79. Crossref, Web of Science, Google Scholar
34. H. Taylor, J. Xie, S. Fox, R. Dunn, A. Arnold and J. Keeffe , The prevalence and causes of vision loss in indigenous Australians: The national indigenous eye health survey, Med. J. Aust. 192 (6) (2010) 312–318. Crossref, Web of Science, Google Scholar
35. M. J. J. P. Van Grinsven, A. Chakravartyy, J. Sivaswamy, T. Theelen, B. van Ginneken and C. I. S´anchez , A bag of words approach for discriminating between retinal images containing exudates or drusen, 2013 IEEE 10th Int. Symp. Biomedical Imaging: From Nano to Macro, San Francisco, CA, USA, 7–11 April 2013. Google Scholar
36. X. Wang , Robust Image Retrieval Based on color Histogram of Local Feature Regions (Springer, Netherlands, 2009). Google Scholar
37. World Health Organization, Diabetes programme (2012), Available at http://www.who.int/diabetes/en. Google Scholar
38. C. Xu and J. Prince , Snakes, shapes, and gradient vector flow, IEEE Trans. Images Process. 7 (1998) 359–369. Crossref, Web of Science, Google Scholar
39. N. Younis, D. M. Broadbent, S. P. Harding and J. R. Vora , Prevalence of diabetic eye disease in patients entering a systematic primary care-based eye screening programme, Diabet. Med. 19 (2002) 1014–1021. Crossref, Web of Science, Google Scholar
40. Y. D. Zhang, L. Wu and G. Wei , A new classifier for polarimetric SAR images, Progr. Electromagn. Res. 94 (2009) 83–104. Crossref, Web of Science, Google Scholar
41. K. Zhang, L. Zhang, H. Song and W. Zhou , Active contours with selective local or global segmentation: A new formulation and level set method, Image Vis. Comput. 28 (2010) 668–676. Crossref, Web of Science, Google Scholar