Advertisement

Automatic Segmentation and Detection of Small Bowel Angioectasias in WCE Images

  • Pedro M. VieiraEmail author
  • Catarina P. Silva
  • Dalila Costa
  • Ismael F. Vaz
  • Carla Rolanda
  • Carlos S. Lima
Article

Abstract

Angioectasias are lesions that occur in the blood vessels of the bowel and are the cause of more than 8% of all gastrointestinal bleeding episodes. They are usually classified as bleeding related lesions, however current state-of-the-art bleeding detection algorithms present low sensitivity in the detection of these lesions. This paper proposes a methodology for the automatic detection of angioectasias in wireless capsule endoscopy (WCE) videos. This method relies on the automatic selection of a region of interest, selected by using an image segmentation module based on the Maximum a Posteriori (MAP) approach where a new accelerated version of the Expectation-Maximization (EM) algorithm is also proposed. Spatial context information is modeled in the prior probability density function by using Markov Random Fields with the inclusion of a weighted boundary function. Higher order statistics computed in the CIELab color space with the luminance component removed and intensity normalization of high reflectance regions, showed to be effective features regarding angioectasia detection. The proposed method outperforms some current state of the art algorithms, achieving sensitivity and specificity values of more than 96% in a database containing 800 WCE frames labeled by two gastroenterologists.

Keywords

Capsule endoscopy EM segmentation Machine learning Markov Random Fields Angioectasias 

Notes

Acknowledgments

This work is supported by FCT (Fundação para a Ciência e Tecnologia) with the reference Project UID/EEA/04436/2019 and with the PhD Grant SFRH/BD/92143/2013.

References

  1. 1.
    Barbosa, D., Ramos, J., Lima, C. S. Detection of small bowel tumors in capsule endoscopy frames using texture analysis based on the discrete wavelet transform. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Conference 2008:3012–3015, 2008Google Scholar
  2. 2.
    Boal Carvalho, P., Magalhães, J., Dias de Castro, F., Monteiro, S., Rosa, B., Moreira, M. J., Cotter, J. Suspected blood indicator in capsule endoscopy: a valuable tool for gastrointestinal bleeding diagnosis. Arquivos de Gastroenterol. 54(1):16–20, 2017Google Scholar
  3. 3.
    Deeba, F., Mohammed, S. K., Bui, F. M., Wahid, K. A. A saliency-based unsupervised method for angioectasia detection in capsule endoscopic images. In: The 39th Conference of The Canadian Medical and Biological Engineering/La Societe Canadiénné de Génie Biomédical, 2016Google Scholar
  4. 4.
    Deeba, F., Mohammed, S. K., Bui, F. M., Wahid, K. A. A saliency-based unsupervised method for angiectasia detection in endoscopic video frames. J. Med. Biol. Eng. 38(2), 325–335, 2017.CrossRefGoogle Scholar
  5. 5.
    D’Halluin, P. N., Delvaux, M., Lapalus, M. G., Sacher-Huvelin, S., Ben Soussan, E., Heyries, L., Filoche, B., Saurin, J. C., Gay, G., Heresbach, D. Does the “Suspected blood indicator” improve the detection of bleeding lesions by capsule endoscopy? Gastrointest. Endosc. 61(2), 243–249, 2005.CrossRefGoogle Scholar
  6. 6.
    Fan, G.W., Chen, T. H., Lin, W. P., Su, M. Y., Sung, C. M., Hsu, C. M., Chi, C. T. Angiodysplasia and bleeding in the small intestine treated by balloon-assisted enteroscopy. J. Digest. Dis. 14(3), 113–116, 2013.CrossRefGoogle Scholar
  7. 7.
    Figueiredo, I. N., Kumar, S., Leal, C., Figueiredo, P. N. (2013) Computer-assisted bleeding detection in wireless capsule endoscopy images. Comput. Methods Biomech. Biomed. Eng. 1(4), 198–210.Google Scholar
  8. 8.
    Fu, Y., Zhang, W., Mandal, M., Meng, M. Q. H. Computer-aided bleeding detection in WCE video. IEEE J. Biomed. Health Inf. 18(2), 636–642, 2014.CrossRefGoogle Scholar
  9. 9.
    Hemingway, A.P. Angiodysplasia: current concepts. Postgrad. Med. J. 64(750), 259–63, 1988.CrossRefGoogle Scholar
  10. 10.
    Hwang, S., Oh, J., Cox, J., Tang, S. J., Tibbals, H. F. Blood detection in wireless capsule endoscopy using expectation maximization clustering. In: Medical Imaging 2006: Image Processing, edited by J. M. Reinhardt, J. P. W. Pluim. SPIE, 2006Google Scholar
  11. 11.
    Iakovidis, D. K., Koulaouzidis, A. Automatic lesion detection in capsule endoscopy based on color saliency: closer to an essential adjunct for reviewing software. Gastrointest Endosc 80(5), 877–883, 2014.CrossRefGoogle Scholar
  12. 12.
    Iakovidis, D. K., Koulaouzidis, A. Automatic lesion detection in wireless capsule endoscopy—a simple solution for a complex problem. In: IEEE International Conference on Image Processing (ICIP), IEEE, pp 2236–2240, 2014Google Scholar
  13. 13.
    Iakovidis, D. K., Koulaouzidis, A. Software for enhanced video capsule endoscopy: challenges for essential progress. Nat. Rev. Gastroenterol. Hepatol. 12(3), 172–186, 2015.CrossRefGoogle Scholar
  14. 14.
    Iddan, G., Meron, G., Glukhovsky, A., Swain, P. Wireless capsule endoscopy. Nature 405(6785):417, 2000.CrossRefGoogle Scholar
  15. 15.
    Jung, Y. S., Kim, Y. H., Lee, D. H., Kim, J. H. Active blood detection in a high resolution capsule endoscopy using color spectrum transformation. 2008 International Conference on BioMedical Engineering and Informatics pp 859–862, 2008Google Scholar
  16. 16.
    Karargyris, A., Bourbakis, N. A methodology for detecting blood-based abnormalities in wireless capsule endoscopy videos. In: 2008 8th IEEE International Conference on BioInformatics and BioEngineering, IEEE, pp 1–6, 2008Google Scholar
  17. 17.
    Kodogiannis, V., Boulougoura, M., Wadge, E., Lygouras, J. The usage of soft-computing methodologies in interpreting capsule endoscopy. Eng. Appl. Artif. Intell. 20(4), 539–553, 2007.CrossRefGoogle Scholar
  18. 18.
    Koulaouzidis, A., Iakovidis, D. K. KID: Koulaouzidis-Iakovidis Database for Capsule Endoscopy. 2016. http://is-innovation.eu/kid
  19. 19.
    Lau, P. Y., Correia, P. L. Detection of bleeding patterns in WCE video using multiple features. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Conference 2007:5601–5604, 2007.Google Scholar
  20. 20.
    Li, B., Meng, M. Computer-Aided Detection of Bleeding Regions for Capsule Endoscopy Images. IEEE Trans. Biomed. Eng. 56(4), 1032–1039, 2009.CrossRefGoogle Scholar
  21. 21.
    Liangpunsakul, S., Mays, L., Rex, D. K. Performance of given suspected blood indicator. Am. J. Gastroenterol. 98(12), 2676–2678, 2003.CrossRefGoogle Scholar
  22. 22.
    Noya, F., Alvarez-Gonzalez, M. A., Benitez, R. Automated angiodysplasia detection from wireless capsule endoscopy, IEEE, pp 3158–3161, 2017Google Scholar
  23. 23.
    Pan, G. B., Yan, G. Z., Song, X. S., Qiu, X. l. Bleeding detection from wireless capsule endoscopy images using improved euler distance in CIELab. J. Shanghai Jiaotong Univ. (Sci.) 15(2):218–223, 2010Google Scholar
  24. 24.
    Plasse, J. H. (2013) The EM Algorithm in Multivariate Gaussian Mixture Models using Anderson Acceleration. PhD thesis, Master thesis in applied mathematics, Worcester Polytechnic InstituteGoogle Scholar
  25. 25.
    Pogorelov, K., Ostroukhova, O., Petlund, A., Halvorsen, P., de Lange, T., Espeland, H. N., Kupka, T., Griwodz, C., Riegler, M. Deep learning and handcrafted feature based approaches for automatic detection of angiectasia. In: 2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), IEEE. 2018.  https://doi.org/10.1109/bhi.2018.8333444
  26. 26.
    Regula, J., Wronska, E., Pachlewski, J. Vascular lesions of the gastrointestinal tract. Best Pract. Res. Clin. Gastroenterol. 22(2), 313–328, 2008.CrossRefGoogle Scholar
  27. 27.
    Shvets, A., Iglovikov, V., Rakhlin, A., Kalinin, A. A. Angiodysplasia detection and localization using deep convolutional neural networks. CoRR. 2018. doi: 10.1101/306159.Google Scholar
  28. 28.
    Van Leemput, K., Maes, F., Vandermeulen, D., Suetens, P. Automated model-based tissue classification of MR images of the brain. IEEE Trans. Med. Imaging 18:897–908, 1999.CrossRefGoogle Scholar
  29. 29.
    Vieira, P., Ramos, J., Barbosa, D., Roupar, D., Silva, C., Correia, H., Lima, C. S. Segmentation of small bowel tumor tissue in capsule endoscopy images by using the MAP algorithm. Conference proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society IEEE Engineering in Medicine and Biology Society Conference 2012:4010–4013, 2012.Google Scholar
  30. 30.
    Vieira, P. M., Goncalves, B., Goncalves, C. R., Lima, C. S. Segmentation of angiodysplasia lesions in WCE images using a MAP approach with Markov random fields. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp 1184–1187. http://ieeexplore.ieee.org/document/7590916/
  31. 31.
    Walker, H. F., Ni, P. Anderson acceleration for fixed-point iterations. SIAM J. Num. Anal. 49(4), 1715–1735, 2011.CrossRefGoogle Scholar
  32. 32.
    Warkentin, T., Moore, J. C., Anand, S. S., Lonn, E. M., Morgan, D. G. (2003) Gastrointestinal bleeding, angiodysplasia, cardiovascular disease, and acquired von Willebrand syndrome. Transf. Med. Rev. 17(4), 272–286, 2003.CrossRefGoogle Scholar
  33. 33.
    Weatherall, I. L., Coombs, B. D. Skin color measurements in terms of CIELAB color space values. J. Investig. Dermatol. 99(4), 468–473, 1992.CrossRefGoogle Scholar
  34. 34.
    Woodland, A., Labrosse, F. On the separation of luminance from colour in images. In: Proceedings of the International Conference on Vision, Video and Graphics, Edinburgh, pp 29–36, 2005Google Scholar
  35. 35.
    Yung, D. E., Sykes, C., Koulaouzidis, A. The validity of suspected blood indicator software in capsule endoscopy: a systematic review and meta-analysis. Expert Rev. Gastroenterol. Hepatol. 11(1), 43–51, 2017.CrossRefGoogle Scholar
  36. 36.
    Zheng, Y., Hawkins, L., Wolff, J., Goloubeva, O., Goldberg, E. Detection of lesions during capsule endoscopy: physician performance is disappointing. Am. J. Gastroenterol. 107(4), 554–60, 2012.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2019

Authors and Affiliations

  1. 1.CMEMS-Uminho Research UnitUniversity of MinhoGuimarãesPortugal
  2. 2.Algoritmi CenterUniversity of MinhoGuimaraesPortugal
  3. 3.Life and Health Sciences Research InstituteUniversity of MinhoBragaPortugal
  4. 4.ICVS/3Bś - PT Government Associate LaboratoryBraga/GuimarãesPortugal
  5. 5.Department of GastroenterologyHospital de BragaBragaPortugal

Personalised recommendations