Bleeding Detection Algorithm for Capsule Endoscopy

Authors: Yong-Gyu Lee, Gilwon Yoon

Abstract:

Automatic detection of bleeding is of practical importance since capsule endoscopy produces an extremely large number of images. Algorithm development of bleeding detection in the digestive tract is difficult due to different contrasts among the images, food dregs, secretion and others. In this study, were assigned weighting factors derived from the independent features of the contrast and brightness between bleeding and normality. Spectral analysis based on weighting factors was fast and accurate. Results were a sensitivity of 87% and a specificity of 90% when the accuracy was determined for each pixel out of 42 endoscope images.

Keywords: bleeding, capsule endoscopy, image analysis, weighted spectrum

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1329939

References:

[1] N. Bourbakis, "Detecting abnormal patterns in WCE images" in 5th IEEE Symp. on Bioinformatics and Bioengineering (BIBE-05), 2005, pp. 232-328.
[2] Intromedic Corp., South Korea, www.intromedic.com.
[3] A. Glukhovsky, "Wireless capsule endoscopy", Sensor Review, vol. 23, no. 2, 2003, pp. 128-133.
[4] L. Cui, C. Hu, Y. Zou, and M. Q.-H. Meng, "Bleeding Detection in Wireless Capsule Endoscopy Images by Support Vector Classifier" in 2010 IEEE Int. Conf. on Information and Automation (ICIA), 2010, pp. 1746-1751.
[5] A. Kararhyris, and N. Bourbakis, "A Methodology for Detecting Blood-based Abnormalities in Wireless Capsule Endoscopy Videos" in 8th IEEE Int. Conf. on Bioinformatics and Bio Engineering (BIBE-08), 2008, pp. 1-6.
[6] G. Pan, G. Yan, X. Qui, and J. Cui, "Bleeding Detection in Wireless Capsule Endoscopy Based on Probabilistic Neural Network" Journal of Medical Systems, vol. 34, Jan. 2010.
[7] P. Y. Lau, and P. L. Correia, "Detection of Bleeding patterns in WCE video using multiple features" 29th Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society, 2007, pp. 5601-5604.
[8] S. A. Prahl., Tabulated molar extinction coefficient for hemoglobin in water. Oregon Medical Laser Center 2001. Available at: http://omlc.ogi.edu/spectra/hemoglobin/. Accessed May 13, 2004.
[9] P. Y. Lau, and P. L. Correia, "Analyzing Gastrointestinal Tissue Images using Multiple Features" in 6th Conf. on Telecommunications, Peniche, 2007, pp. 435-438.
[10] C. K. Poh, T. M. Htwe, L. Li, W. Shen, j. Liu, J. H. Lim, K. L. Chan, and P. C. Tan, "Multi-Level Local Feature Classification for Bleeding Detection in Wireless Capsule Endoscopy images" in 2010 IEEE conf. on Cybernetics and Intelligent Systems, 2010, Singapore, pp. 76-81.