Automatic Computer Aided Bleeding Detection Scheme for Wireless Capsule Endoscopy (WCE) Video Based on Higher and Lower Order Statistical Features in a Composite Color
- 116 Downloads
Wireless capsule endoscopy (WCE) offers noninvasive means to diagnose intestinal anomalies like bleeding. However, one of the problems here is the time consuming complex reviewing process which calls for automatic computer aided bleeding detection techniques to reduce the burden of the physicians. In this paper, pixel based holistic feature extraction scheme is proposed for bleeding frame detection of WCE recordings. Unlike conventional methods, instead of directly using RGB (red, green, blue) color space, a transform color domain is introduced. Higher and lower order statistical analysis on that composite color domain are carried out to extract features from the given WCE image. Feature-based supervised classification using support vector machine is performed to differentiate bleeding and non-bleeding images. Next, in order to improve the bleeding frame detection performance in WCE video, a post-processing scheme is developed utilizing the variation in temporal characteristics of consecutive frames. Finally, a zone detection algorithm is proposed to identify bleeding regions in the detected bleeding images where some morphological operations are also used. Extensive experimentation is carried out on a numerous number of WCE images and videos. It is observed that the proposed algorithm can detect bleeding frame and zones from WCE video recordings with a satisfactory level of performance.
KeywordsBleeding detection Bleeding zone Color intensity ratio Feature extraction Wireless capsule endoscopy
The authors would like to express their earnest gratefulness towards Dr. M. G. Kibria and Dr. S. N. F. Rumi of Dhaka Medical College and Hospital, Dhaka, Bangladesh, for assisting us to find the bleeding images of a WCE video and delineate the bleeding zones of a bleeding image.
- 1.Adler, D. G., & Gostout, C. J. (2003). Wireless capsule endoscopy. Hospital Physician, 39, 14–22.Google Scholar
- 8.Sainju, S., Bui, F. M., & Wahid, K. (2013). Bleeding detection in wireless capsule endoscopy based on color features from histogram probability. In Canadian Conference on Electrical and Computer Engineering, 2013, pp. 1–4.Google Scholar
- 9.Ghosh, T., Wahid, K., & Fattah, S. A. (2014). Automatic bleeding detection in wireless capsule endoscopy based on RGB pixel intensity ratio. In International Conference on Electrical Engineering and Information Communication Technology, iCEEiCT-2014, pp. 1–4.Google Scholar
- 10.Ghosh, T., Bashar, S. K., Alam, M. S., Wahid, K., & Fattah, S. A. (2014). A statistical feature based novel method to detect bleeding in wireless capsule endoscopy images. In International Conference on Informatics Electronics and Vision, ICIEV-2014, pp. 1–4.Google Scholar
- 13.Gao, W., Zhang, X., Yang, L., & Liu, H. (2010). An improved sobel edge detection. In 3rd International Conference on Computer Science and Information Technology, ICCSIT, pp. 67–71.Google Scholar
- 14.The Capsule Endoscopy Website. (2014). Capsule endoscopy videos. Retrieved from http://www.capsuleendoscopy.org.
- 18.Conversano, F., Casciaro, E., Franchini, R., Casciaro, S., Lay-Ekuakille, A. (2014). Fully automatic 3D segmentation measurements of human liver vessels from contrast-enhanced CT. In IEEE International Symposium on Medical Measurements and Applications, MeMeA, pp. 1–5.Google Scholar