|
Vol: 59(73) No: 2 / December 2014 Automated microaneurysm detection of digital fundus images using shape and size features Petra Varsányi Institute of Applied Informatics, Óbuda University, John von Neumann Faculty of Informatics, Bécsi út 96/b, 1134 Budapest, Hungary, phone: (361) 666-5550, e-mail: petra.varsanyi@gmail.com Zsolt Fegyvári Institute of Applied Informatics, Óbuda University, John von Neumann Faculty of Informatics, Bécsi út 96/b, 1134 Budapest, Hungary, e-mail: fegyvari.zsolt@gmail.com Szabolcs Sergyán Institute of Applied Informatics, Óbuda University, John von Neumann Faculty of Informatics, Bécsi út 96/b, 1134 Budapest, Hungary, e-mail: sergyan.szabolcs@nik.uni-obuda.hu Zoltán Vámossy Institute of Applied Informatics, Óbuda University, John von Neumann Faculty of Informatics, Bécsi út 96/b, 1134 Budapest, Hungary, e-mail: vamossy.zoltan@nik.uni-obuda.hu, web: http://nik.uni-obuda.hu Keywords: medical image processing, microaneurysm detection, image segmentation, skeletonization Abstract In diabetic retinopathy it is very important to find microaneurysm in digital fundus camera images. The appearance of microaneurysms is one of the first symptoms of the disease. Our aim is to detect visible microaneurysms in retina using size and shape features of objects in images. The proposed algorithm has three main parts. First, in the pre-processing step, the original image is binarized, and in the binarized image only vessels and microaneurysms candidates can be found. In the second phase of the algorithm the blood vessel is determined, and then the microaneurysm candidates are classified in the third step. The goal is to detect as many as possible microaneurysms considering their shape and size features. Experiments with manual settings on the test images showed approx. 50% of detection performance, and it can be further improved by development of pre-processing and increasing classification criteria. The developed system can help the manual evaluation of microaneurysms, hence can accelerate the work of doctors. References [1] E.-M Kohner and M. Sleightholm, “Does microaneurysm count reflect severity of early diabetic retinopathy?” Ophthalmology, vol. 93, no. 5, pp. 586-589, May 1986. [2] T. Kauppi, V. Kalesnykiene, J.-K. Kamarainen, L. Lensu, I. Sorri, A. Raninen, R. Voutilainen, H. Uusitalo, H. Kälviáinen, and J. Pietilä, “DIARETB1 diabetic retinopathy database and evaluation protocol,” Machine Vision and Pattern Recognition Research Group, Lappeenranta University of Technology, Tech. Rep., 2006. [3] J. Tick, Cs. Imreh, and Z. Kovács, “Business process modeling and the robust PNS problem,” Acta Polytechnica Hungarica, vol. 10, no. 6, pp. 193-204, 2013. [4] S. Szénási, “Medical image segmentation with split-and-merge method,” in 5th IEEE International Symposium on Logistics and Industrial Informatics, Wildau, Germany, September 5-7. 2013, pp. 137-140. [5] S. Szénási, “Genetic algorithm for parameter optimization of image segmentation algorithm,” in 14th IEEE International Symposium on Computational Intelligence and Informatics, Budapest, Hungary, November 19-21. 2013, pp. 351-354. [6] T. Walter and J. Klein, “Automatic detection of microaneurysms in color fundus images of human retina by means of the bounding box closing,” Lecture Notes in Computer Science, vol. 2526, pp. 210-220, 2002. [7] J. Frame, P. Undrill, M. Cree, J. Olson, K. McHardy, P. Sharp, and J. Forrester, “A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic uorescein angiograms,” Computers on Biology and Medicine, vol. 28, pp. 225-238, 1998. [8] L. Xu and S. Luo, “A novel method for blood vessel detection from retinal images,” BioMedical Engineering Online, vol. 9, no. 14, pp. 1-10, 2010. [9] L. Streeter and M. Cree, “Microaneurysm detection in colour fundus images,” in Image and Vision Computing New Zealand, Palmerston North, New Zealand, November 2003, pp. 280-285. [10] I. Lazar and A. Hajdu, “Microaneurysm detection in retinal images using a rotating cross-section based model,” in IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Chicago, IL, March 30 – April 2 2011, pp. 1405-1409. [11] C. Sinthanayothin, J. Boyce, T. Williamson, H. Cook, E. Mensah, S. Lal, and D. Usher, “Automated detection of diabetic retinopathy on digital fundus images,” Diabetic Medicine, vol. 19, no. 2, pp. 105-112, February 2002. [12] C. Serrano, B. Acha, and S. Revuelto, “2D adaptive filtering and region growing algorithm for the detection of microaneurysms in retinal angiograms,” in Proc. SPIE, Medical Imaging: Image Processing, J. M. Fitzpatrick and M. Sonka, Eds., vol. 5370, San Diego, CA, May 12 2004. [13] K. Zuiderveld, Graphic gems. San Diego, CA: Academic Press Professional, 1994, vol. v, ch. Contrast limited adaptive histogram equalization, pp. 474-485. [14] R. Ohlander, K. Price, and D. R. Reddy, “Picture segmentation using a recursive region splitting method,” Computer Graphics and Image Processing, vol. 8, no. 3, pp. 313-333, December 1978. [15] S. Szénási and Z. Vámossy, “Evolutionary algorithm for optimizing parameters of GPGPU-based image segmentation,” Acta Polytechnica Hungarica, vol. 10, no. 5, pp. 7-28, 2013. [16] S. Szénási, “Segmentation of colon tissue sample images using multiple graphics accelerators,” Computers in biology and medicine, vol. 51, pp. 93-103, 2014 [17] Gy. Györök and A. Sáfár, “Heat shock repression by microcontroller smart control,” Scientific Bulletin of Politechnica University of Timisoara Transactions on Automatic Control and Computer Science, vol. 57, no. 2, pp. 109-112, 2013. [18] J. Tick, Z. Kovács, and F. Friedler, “Synthesis of optimal workflow structure,” Journal of Universal Computer Science, vol. 12, no. 9, pp. 1385-1392, 2006. [19] J. Tick, “Potential application of p-graph-based workflow in logistics,” Aspects of Computational Intelligence: Theory and Applications, pp. 293-303, 2013. [20] P. Varsányi, Zs. Fegyvári, Sz. Sergyán, and Z. Vámossy, “Manual microaneurysm detection support with size- and shape-based detection,” in 9th IEEE International Symposium on Applied Computational Intelligence and Informatics, Timisoara, Romania, May 15-17 2014, pp. 361-365. |