|
Vol: 58(72) No: 1 / March 2013 Informative Frames Detection in Wireless Capsule Videos Using Gabor Filters Mihaela Ionescu Department of Medical Informatics, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania Cristin Constantin Vere Research Centre of Gastroenterology and Hepatology, University of Medicine and Pharmacy Craiova, 2-4 Petru Rares Street, 200349 Craiova, Romania, phone: (0040) 351-443561, e-mail: vere_cristin@yahoo.com Oana Astrid Vătămanu Department of Medical Informatics, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania Anca Tudor Department of Medical Informatics, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania Gheorghe-Ioan Mihalaş Department of Medical Informatics, University of Medicine and Pharmacy “Victor Babes”, Timisoara, Romania Keywords: wireless capsule endoscopy, Gabor filters, image segmentation, edge detection Abstract Wireless capsule video endoscopy is a modern clinical technique resulting in a set of qualitative images of the interior of the small bowel, offering great accuracy in the evaluation and diagnosis of small bowel lesions. Its major drawback is represented by the increased amount of time needed for the visualization of more than 60000 acquired frames per patient. Image processing techniques such as segmentation and classification play an important role in video endoscopy analysis, aiming to partition the content of an image in a set of distinct, homogenous regions, characterized by a set of properties like colour, texture, edges, hue, saturation, facilitating lesion detection and evaluation. Material and methods: Digital images are represented as arrays of discrete spatial and intensity information, so they may be submitted to different digital image processing techniques, mainly for improved visualisation, quantitative analysis and abstract interpretation. This paper used Gabor filters for the analysis of 38 sets of frames extracted from 14 wireless capsule videos obtained after investigating patients with different gastrointestinal pathology. Results: Our analysis was meant to complete and assist the physician in establishing a correct diagnosis for 4 types of lesions: intestinal polyps, telangiectasia, celiac disease and tumours / formations, where texture and edge segmentation offered very good success rates. Conclusion: Applied to wireless capsule frames, Gabor filters are powerful tools for edge detection and texture discrimination. References [1] R. Tersigni and C. Prantera, “Crohn\'s Disease - A Multidisciplinary Approach”, Springer-Verlag Italia, 2010. [2] C.A. Solem, E. Loftus Jr., J.G. Fletcher, T.H. Baron, C.J. Gostout, B.T. Petersen el al, “Small-bowel imaging in Crohn’s disease: a prospective, blinded, 4-way comparison trial”, Gastrointestinal Endoscopy, vol. 68, no. 2, 2008. [3] M.P. Federle, “CT of the small intestine: Enterography and angiography”, Supplement to Applied Radiology, 2007. [4] S.R. Paulsen, J.E. Huprich, J.G. Fletcher et al, “CT enterography as a diagnostic tool in evaluating small bowel disorders: review of clinical experience with over 700 cases”, Radiographics; 26:641-57, discussion 657–62, 2006. [5] I. Markova, K. Kluchova, R. Zbori, M. Mashlan, M. Herman, “Small bowel imaging – Still a radiologic approach?”, Biomed Pap Med, vol. 154, no. 2, pp. 123-132, Jun. 2010. [6] C.C. Vere, “Tehnici moderne de diagnostic si tratament in patologia organica a intestinului subtire”, Editura Medicala Universitara, Craiova, 2010. [7] C.C. Vere, F. Sima, F. Ţapu and T. Ciurea, “Videocapsula endoscopica si enteroscopia cu balon, metode moderne de explorare a intestinului subtire”, in Craiova Medicala, vol 10, nr 1, 2008. [8] C. Petruzziello, S. Onali, E. Calabrese, F. Zorzi et al., “Wireless capsule endoscopy and proximal small bowel lesions in Crohn’s disease”, World J Gastroenterol; 16(26): pp. 3299-3304, July 2010. [9] E. Rondonotti, “Capsule endoscopy - The revolution of small bowel endoscopy”, Vrije Universiteit, 2008. [10] M. Hadithi, G.D. Heine, M.A. Jacobs, A.A. van Bodegraven, C.J. Mulder, “A prospective study comparing video capsule endoscopy with double-balloon enteroscopy in patients with obscure gastrointestinal bleeding”, Gastroenterology, vol. 131, no. 1, pp. 327-329, July 2006. [11] G. Dougherty, “Digital Image Processing for Medical Applications”, Cambridge University Press, 2009. [12] T.M. Deserno, “Biomedical Image Processing”, Springer Heidelberg Dordrecht London New York, 2011. [13] C. Solomon and T. Breckon, “Fundamentals of Digital Image Processing - A Practical Approach with Examples in Matlab”, Wiley Blackwell, 2011. [14] D. J. Gabor, “Theory of communication”, IEE, vol. 93, no. 26, pp. 429–457, 1946. [15] A.C. Bovik, M. Clark and W. S. Geisler, “Multichannel texture analysis using localized spatial filters,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 1, pp. 57–73, 1990. [16] J. G. Daugman, “Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters”, Journal of the Optical Society of America A, 2(7), pp. 1160–1169, July 1985. [17] A. Olowoyeye, M. Tuceryan, S. Fang, “Medical Volume Segmentation using Bank of Gabor Filters”, ACM 978-1-60558-166-8/09/03, 2009. [18] S.E. Grigorescu, N. Petkov and P. Kruizinga, “Comparison of Texture Features Based on Gabor Filters”, IEEE Trans Image Processing, vol. 11, no. 10, pp. 1160-1176, October 2002. [19] A. Karargyris, “Identification of polyps in Wireless Capsule Endoscopy videos using Log Gabor filters”, IEEE/NIH Life Science Systems and Applications Workshop, LiSSA, pp. 143-147, April 2009.. [20] A. Karargyris, N. Bourbakis, “Detection of Small Bowel Polyps and Ulcers in Wireless Capsule Endoscopy Videos”, IEEE Trans. Biomedical Engineering, vol. 58, no. 10, pp. 2777-2786, Oct. 2011. [21] Q. Zhao, T. Dassopoulos, G. Mullin, G. Hager, M.Q. Meng and R. Kumar, “Towards integrating temporal information in capsule endoscopy image analysis”, Engineering in Medicine and Biology Society,EMBC, pp. 6627-6630, Sept. 2011. [22] T. Randen, J. H. Husoy, “Filtering for texture classification: a comparative study,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 21, no. 4, pp. 291-310, Apr. 1999. [23] M. Ionescu, C.C. Vere, O.A. Vatamanu, A. Tudor, G.I. Mihalas, “Image processing techniques applied on wireless capsule videos obtained from patients with gastrointestinal pathology”, 32nd National Conference on Medical Informatics (RO-MEDINF 2012), Timisoara, Romania, Nov. 2012. |