Advertisement

Polyp Segmentation in NBI Colonoscopy

  • Sebastian Gross
  • Manuel Kennel
  • Thomas Stehle
  • Jonas Wulff
  • Jens Tischendorf
  • Christian Trautwein
  • Til Aach
Part of the Informatik aktuell book series (INFORMAT)

Abstract

Endoscopic screening of the colon (colonoscopy) is performed to prevent cancer and to support therapy. During intervention colon polyps are located, inspected and, if need be, removed by the investigator. We propose a segmentation algorithm as a part of an automatic polyp classification system for colonoscopic Narrow-Band images. Our approach includes multi-scale filtering for noise reduction, suppression of small blood vessels, and enhancement of major edges. Results of the subsequent edge detection are compared to a set of elliptic templates and evaluated. We validated our algorithm on our polyp database with images acquired during routine colonoscopic examinations. The presented results show the reliable segmentation performance of our method and its robustness to image variations.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gesundheitsberichterstattung des Bundes. Krebs in Deutschland 2003–2004: Häufigkeiten und Trends. 8th ed. Robert Koch Institut, Gesellschaft der epidemiologischen Krebsregister in Deutschland e.V.; 2008.Google Scholar
  2. 2.
    Tischendorf JJW, Wasmuth HE, Koch A, et al. Value of magnifying chromoendoscopy and narrow band imaging (NBI) in classifying colorectal polyps: A prospective controlled study. Endoscopy. 2007;39(12):1092–6.CrossRefGoogle Scholar
  3. 3.
    Bourbakis N. Detecting abnormal patterns in WCE images. Procs IEEE BIBE. 2005; p. 232–238.Google Scholar
  4. 4.
    Kang J, Doraiswami R. Real-time image processing system for endoscopic applications. In: Canadian Conference on Electrical and Computer Engineering (IEEE CCECE). vol. 3; 2003. p. 1469–1472.Google Scholar
  5. 5.
    Hwang S, Oh J, Tavanapong W,et al. Polyp detection in colonoscopy video using elliptical shape feature. Procs ICIP. 2007;2:II–465–II–468.Google Scholar
  6. 6.
    Stehle T, Gross S, Behrens A,et al. Classification of colon polyps in NBI endoscopy using vascularization features. Procs SPIE. 2009;To appear.Google Scholar
  7. 7.
    Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell. 1990;12(7):629–639.CrossRefGoogle Scholar
  8. 8.
    Weickert J. Anisotropic Diffusion in Image Processing. Universität Kaiserslautern; 1996. Available from: http://www.mia.uni-saarland.de/weickert/Papers/diss.ps.gz.Google Scholar
  9. 9.
    Gross S, Stehle T, Behrens A, et al. RealTimeFrame: A real time image processing solution for medical environments. In: 41. DGBMT-Jahrestagung Biomedizinische Technik (BMT). Aachen; 2007.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sebastian Gross
    • 1
    • 2
  • Manuel Kennel
    • 1
  • Thomas Stehle
    • 1
  • Jonas Wulff
    • 1
  • Jens Tischendorf
    • 2
  • Christian Trautwein
    • 2
  • Til Aach
    • 1
  1. 1.Institute of Imaging & Computer VisionRWTH Aachen UniversityGermany
  2. 2.Medical Department IIIRWTH Aachen University HospitalGermany

Personalised recommendations