Real-Time Image Analysis of Capsule Endoscopy for Bleeding Discrimination in Embedded System Platform
Image processing for capsule endoscopy requires large
memory and it takes hours for diagnosis since operation time is
normally more than 8 hours. A real-time analysis algorithm of capsule
images can be clinically very useful. It can differentiate abnormal
tissue from health structure and provide with correlation information
among the images. Bleeding is our interest in this regard and we
propose a method of detecting frames with potential bleeding in
real-time. Our detection algorithm is based on statistical analysis and
the shapes of bleeding spots. We tested our algorithm with 30 cases of
capsule endoscopy in the digestive track. Results were excellent where
a sensitivity of 99% and a specificity of 97% were achieved in
detecting the image frames with bleeding spots.
[1] D. G. Adler and C. J. Gostout, "Wireless Capsule Endoscopy", Hospital
Physician, 2003, pp.14-22.
[2] A. karargyris and N. Bourbakis, "ASurvey on WCE Imaging Systems and
Techniques," IEEE Engineering in Medicine and Biology Magazine, Vol.
29, no. 1, 2010
[3] Intromedic Co., South Korea, www.intromedic.com.
[4] N. Bourbakis, "Detecting abnormal patterns in WCE images," in 5th IEEE
Symp. on Bioinformatics and Bioengineering (BIBE-05), Minneapolis,
2005, pp. 26-29.
[5] B. Li and M. Q.-H. Meing, "Analysis of the gastrointestinal status from
wireless capsule endoscopy images using local color feature," in Proc. the
2007 Inter. Conf. Information Acquisition, Korea, 2007, pp. 553-557.
[6] J. G. Webster, Design of Pulse Oximeters. Bristol and Philadelphia, CA:
Institute of Physics Publishing, 1997, ch. 4.
[7] J. Lee, J. OH,X. Yuan and S.-J. Tang, "Automatic classification of
digestive organs in wireless capsule Endoscopy Videos," in Proceedings
of the 2007 ACM symposium on Applied computing, 2007, pp.
1041-1045.
[8] P. Y. Lau, and P. L. Correia, "Detection of Bleeding patterns in WCE
video using multiple features," in 29th Annual Int. Conf. of the IEEE
Engineering in Medicine and Biology Society, 2007, pp. 5601-5604.
[9] B. Giritharan, X. Yuan, J. Liu, B. Buckles, J. Oh and S. J. Tang,
"Bleeding Detection from Capsule Endoscopy Videos," in 30th Annu.
IEEE EBMS Conf., Vancouver, 2008, pp. 4780-4783.
[10] A. Karargyris and N. Bourbakis, "A Methodology for Detection
Blood-based Abnormalities in Wireless Capsule Endoscopy Videos," in
8th IEEE Inter. Conf. Bioinformatics and Bioengineering, Athens, 2008,
pp. 1-6.
[11] Y. S. Jung, Y. H. Kim, D. H. Lee and J. H. Kim, "Active Blood Detection
in a High Resolution Capsule Endoscopy using Color Spectrum
Transformation," in Int. Conf. BioMedical Engineering and Informatics
(BMEI), Sanya, 2008, pp. 859-862.
[12] 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, Singapore , 2010, pp. 76-81.
[1] D. G. Adler and C. J. Gostout, "Wireless Capsule Endoscopy", Hospital
Physician, 2003, pp.14-22.
[2] A. karargyris and N. Bourbakis, "ASurvey on WCE Imaging Systems and
Techniques," IEEE Engineering in Medicine and Biology Magazine, Vol.
29, no. 1, 2010
[3] Intromedic Co., South Korea, www.intromedic.com.
[4] N. Bourbakis, "Detecting abnormal patterns in WCE images," in 5th IEEE
Symp. on Bioinformatics and Bioengineering (BIBE-05), Minneapolis,
2005, pp. 26-29.
[5] B. Li and M. Q.-H. Meing, "Analysis of the gastrointestinal status from
wireless capsule endoscopy images using local color feature," in Proc. the
2007 Inter. Conf. Information Acquisition, Korea, 2007, pp. 553-557.
[6] J. G. Webster, Design of Pulse Oximeters. Bristol and Philadelphia, CA:
Institute of Physics Publishing, 1997, ch. 4.
[7] J. Lee, J. OH,X. Yuan and S.-J. Tang, "Automatic classification of
digestive organs in wireless capsule Endoscopy Videos," in Proceedings
of the 2007 ACM symposium on Applied computing, 2007, pp.
1041-1045.
[8] P. Y. Lau, and P. L. Correia, "Detection of Bleeding patterns in WCE
video using multiple features," in 29th Annual Int. Conf. of the IEEE
Engineering in Medicine and Biology Society, 2007, pp. 5601-5604.
[9] B. Giritharan, X. Yuan, J. Liu, B. Buckles, J. Oh and S. J. Tang,
"Bleeding Detection from Capsule Endoscopy Videos," in 30th Annu.
IEEE EBMS Conf., Vancouver, 2008, pp. 4780-4783.
[10] A. Karargyris and N. Bourbakis, "A Methodology for Detection
Blood-based Abnormalities in Wireless Capsule Endoscopy Videos," in
8th IEEE Inter. Conf. Bioinformatics and Bioengineering, Athens, 2008,
pp. 1-6.
[11] Y. S. Jung, Y. H. Kim, D. H. Lee and J. H. Kim, "Active Blood Detection
in a High Resolution Capsule Endoscopy using Color Spectrum
Transformation," in Int. Conf. BioMedical Engineering and Informatics
(BMEI), Sanya, 2008, pp. 859-862.
[12] 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, Singapore , 2010, pp. 76-81.
@article{"International Journal of Medical, Medicine and Health Sciences:51374", author = "Yong-Gyu Lee and Gilwon Yoon", title = "Real-Time Image Analysis of Capsule Endoscopy for Bleeding Discrimination in Embedded System Platform", abstract = "Image processing for capsule endoscopy requires large
memory and it takes hours for diagnosis since operation time is
normally more than 8 hours. A real-time analysis algorithm of capsule
images can be clinically very useful. It can differentiate abnormal
tissue from health structure and provide with correlation information
among the images. Bleeding is our interest in this regard and we
propose a method of detecting frames with potential bleeding in
real-time. Our detection algorithm is based on statistical analysis and
the shapes of bleeding spots. We tested our algorithm with 30 cases of
capsule endoscopy in the digestive track. Results were excellent where
a sensitivity of 99% and a specificity of 97% were achieved in
detecting the image frames with bleeding spots.", keywords = "bleeding, capsule endoscopy, image processing, real
time analysis", volume = "5", number = "11", pages = "529-5", }