automatic detection of retinal hemorrhage based on gabor wavelet and hybrid knnsvm algorithm for fundus images
Karunya Karo Shanthi Y,Karpagam V
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:2 Issue:1 Year: 08 February,2014 Pages:50-57
Abstract
Retinal hemorrhage is the abnormal bleeding of the blood vessels in the retina, the membrane in the back of the eye. In retinal image, automated detection of hemorrhage is a major challenging factor. For automated detection of hemorrhage, a generalized framework is need to train a classifiers with optimal features learned from available dataset. Because of the variability in appearance of these lesions(i.e., hemorrhages), different techniques had been designed to detect each type of these lesions(i.e., hemorrhages) separately in detection system. We need a generalized framework to detect these types of lesions in fundus (i.e., retinal) image. A robust and computationally efficient approach for hemorrhage detection in a fundus retinal image is presented in this paper. Splat feature classification method is proposed with application to retinal hemorrhage detection in fundus images. Automated screening system is very much important to detect a retinal hemorrhages. Based on the supervised approach, fundus images are partitioned into non overlapping segments covering the entire image. Each splat contains a similar color and spatial location. A set of features is extracted from each splat using the GLCM & Gabor Wavelet. These features’ describes a characteristic relative to each pixel in a splat. Supervised classification predicts the likelihood of splats being hemorrhages with the optimal features subset selected in a two-step feature selection process. Preliminary feature selection is done by filter approach followed by a wrapper approach. Hybrid KNNSVM classifier is trained with expert annotation. From the resulting hemorrhageness map, a hemorrhage index is assigned. A classifier could evaluate on the publically available dataset. This work will provide a greater AUC in splat level and image level. Our approaches can potential to be applied to other detection tasks.
Kewords
Diabetic retinopathy (DR), fundus images, retinal hemorrhage, KNN, Hybrid KNNSVM, Support Vector Machine, Gabor Wavelet.
Reference
[1] M. D. Abràmoff, J. M. Reinhardt, S. R. Russell, J. C. Folk, V. B. Mahajan, M. Niemeijer, and G. Quellec, “Automated early detection of diabetic retinopathy,” Ophthalmology, no. 6, pp. 1147–1154, Apr. [2] O. Faust, R. AcharyaU., E. Y. K. Ng,K.-H. Ng, and J. S. Suri, “Algorithms for the automated detection of diabetic retinopathy using digital fundus images: A review,” J. Med. Syst., Apr. [3] P. Jitpakdee, P. Aimmanee, and B. Uyyanonvara, “A survey on hemorrhage detection in diabetic retinopathy retinal images,” in Proc. 9th Int. Conf. Elect. Eng./Electron., Comput., Telecommun. Inf. Technol.(ECTI-CON), Bangkok, Thailand, 2012, pp. 1–4, vol.. [4] M. Abràmoff, M. Garvin, and M. Sonka, “Retinal imaging and image analysis,” IEEE Rev. Biomed. Eng., vol. 3, pp. 169–208, 2010. [5] S. C.H.Hoi, R. Jin, J. Zhu, andM. R. Lyu, “Batchmode active learning and its application to medical image classification,” in Proc. ICML, 2006, pp. 417–424. [6] J. Fairfield, “Toboggan contrast enhancement for contrast segmentation,” in Proc. Int. Conf. Pattern Recognit., 1990, vol. 1, pp. 712–716. [7] C. Sànchez, M. Niemeijer, M. Abràmoff, and B. vanGinneken, “Active learning for an efficient training strategy of computer-aided diagnosis systems: Application to diabetic retinopathy screening,” Med. Image Comput. Comput. Assist. Intervent., vol. 13, no. 3, pp. 603–610, 2010. [8] Li Tang; Niemeijer, M.; Reinhardt, J.M.; Garvin, M.K.; Abramoff, M.D., "Splat Feature Classification With Application to Retinal Hemorrhage Detection in Fundus Images," Medical Imaging, IEEE Transactions on , vol.32, no.2, pp.364,375, Feb. 2013 [9] A. Kannan1, V. Mohan2, N. Anbazhagan3 “ MR Images Classification Using Hybrid KNNSVM Algorithm “Signal Processing Research (SPR), vol.1, Issue 1, Dec 2012
