Bleeding Detection in Wireless Capsule Endoscopy Based on Probabilistic Neural Network
- 514 Downloads
Wireless Capsule Endoscopy (WCE), which allows clinicians to inspect the whole gastrointestinal tract (GI) noninvasively, has bloomed into one of the most efficient technologies to diagnose the bleeding in GI tract. However WCE generates large amount of images in one examination of a patient. It is hard for clinicians to leave continuous time to examine the full WCE images, and this is the main factor limiting the wider application of WCE in clinic. A novel intelligent bleeding detection based on Probabilistic Neural Network (PNN) is proposed in this paper. The features of bleeding region in WCE images distinguishing from non-bleeding region are extracted. A PNN classifier is built to recognize bleeding regions in WCE images. Finally the intelligent bleeding detection method is implemented through programming. The experiments show this method can correctly recognize the bleeding regions in WCE images and clearly mark them out. The sensitivity and specificity on image level are measured as 93.1% and 85.6% respectively.
KeywordsWireless capsule endoscopy Gastrointestinal tract Probabilistic neural network Bleeding detection
This research was supported by the National Hi-Tech Research and Development Program (863) of China (2006AA04Z368) and the National Natural Science Foundation of China (30570485).
- 1.National digestive diseases information clearinghouse. Bleeding in the digestive tract. Bethesda: National Institutes of Health, 7:1–6, 2004.Google Scholar
- 4.Swain, P., Iddan, G.J., Meron, G., and Glukhovsky, A., Wireless capsule endoscopy of the small bowel: development, testing, and first human trials. Biomonitoring and Endoscopy Technologies, Amsterdam, Netherlands, SPIE, 4158:19–23, 2001.Google Scholar
- 6.Kameda, N., Higuchi, K., Shiba, M., Tabuchi, M., Sugimori, S., Yukawa, T., Kadouchi, K., Okazaki, H., Machida, H., Inagawa, M., Wada, T., Tanigawa, T., Yamagami, H., Watanabe, K., Watanabe, T., Tominaga, K., Fujiwara, Y., Oshitani, N., and Arakawa, T., A prospective trial comparing wireless capsule endoscopy and double-balloon enteroscopy in patients with obscure gastrointestinal bleeding. Gastrointest. Endosc. 63(5):AB162–AB162, 2006.CrossRefGoogle Scholar
- 8.Canlas, K. R., Dobozi, B. M., Lin, S., Smith, A. D., Rockey, D. C., Muir, A. J., Agrawal, N. M., Poleski, M. H., Patel, K., and McHutchison, J. G., Using capsule endoscopy to identify GI tract lesions in cirrhotic patients with portal hypertension and chronic anemia. J. Clin. Gastroenterol. 42(7):844–848, 2008.CrossRefGoogle Scholar
- 10.Buscaglia, J. M., Giday, S. A., Kantsevoy, S. V., Clarke, J. O., Magno, P., Yong, E., and Mullin, G. E., Performance characteristics of the suspected blood indicator feature in capsule endoscopy according to indication for study. Clin. Gastroenterol. Hepatol. 6(3):298–301, 2008.CrossRefGoogle Scholar
- 12.Mackiewicz, M., Fisher, M., and Jamieson, C., Bleeding detection in Wireless Capsule Endoscopy using adaptive colour histogram model and Support Vector Classification. Medical Imaging 2008 Conference, San Diego, CA, SPIE, 6914: R1–R12, 2008.Google Scholar
- 13.Bourbakis, N., Makrogiannis, S., and Kavraki, D., A neural network-based detection of bleeding in sequences of WCE images. 5th IEEE Symposium on Bioinformatics and Bioengineering, Minneapolis, MN, IEEE Computer Soc, 324–327, 2005.Google Scholar
- 14.Li, B.P., and Meng, Q.H., Computer aided detection of bleeding in capsule endoscopy images. 2008 Canadian Conference on Electrical and Computer Engineering, Niagara Falls, CANADA, 1875-1878, 2008.Google Scholar
- 16.Hwang, S., Oh, J., Cox, J., Tang, S.J., and Tibbals, H.F., Blood detection in wireless capsule endoscopy using expectation maximization clustering. Medical Imaging 2006: Image Processing, San Diego, CA, USA, SPIE, 6144:1–11.Google Scholar
- 17.Jung, Y.S., Kim, Y.H., Lee, D.H., and Kim, J.H., Active blood detection in a high resolution capsule endoscopy using color spectrum transformation. International Conference on BioMedical Engineering and Informatics, Washington, DC, USA, IEEE, 1:859–862.Google Scholar
- 19.The Mathworks, Probabilistic Neural Networks. http://www.mathworks.com/access/helpdesk/help/toolbox/nnet/index.html. [15, September 2009].