Automatic and Diagnosis-supporting Detection of Polyps in Colonoscopic Image Sequences

The Challenge: Automatic Polyp Detection in Colonoscopy Videos

Colon cancer is the second leading cause of cancer death. Around 26,000 people die in Germany each year as a result. In 90 percent of these cases, special colon polyps serve as precursors to cancer. For this reason, periodic colonoscopy-based cancer screening for people 55 years and older is now covered under Germany´s statutory health insurance program. During a colonoscopy, the large intestine and rectum are examined with an endoscope. The effectiveness of this procedure depends heavily on the experience and attentiveness of the physician. Various studies show that 12 to 24 percent of the polyps go undetected, a rate that could be considerably lowered by instituting automatic polyp detection with image-generating processes. The real challenge is identifying small polyps and new formations that are flat and still under the surface.

Our Approach: KoloPol

As part of its own basic research, the Fraunhofer Institute for Integrated Circuits IIS developed an analysis process in which suspicious tissue areas with pigment and texture deviations are highlighted and automatically detected. This development laid the foundations for a method that supports the physician by automatically visualizing suspicious areas and documenting detected polyps. A further step in the “KoloPol“ project (german) will involve testing the functionality of such image detection methods under actual clinical conditions, including fine-tuning the ability to identify smaller and flatter polyps. With this software researchers hope to not only increase the polyp detection rate, but also reduce the time and effort associated with colon cancer screening.

First Result: Prototype

KoloPol – Biophantom for Colonoscopy
© Fraunhofer IIS
KoloPol – Biophantom for Colonoscopy

At Medica 2015 in Düsseldorf, a first prototype was presented as a result of the project which recognizes retrospectively colonoscopic polyp video sequences in real-time. Together with the Medical Clinic II (Prof. Dr. Martin Raithel) of the hospital Waldkrankenhaus St. Marien Erlangen, the developed system was verified in a lengthy attempt at a biomodel of a pig colon with sewn polyps in January 2016.

During the annual meeting of the German Society for Endoscopy and Imaging Procedures (DGE-BV) in Mannheim from March 17 to 19, 2016, the developed system for polyp detection was presented to the public and carried out in an evaluation by experts (incl. eye tracking).

Automatic Polyp Detection in Real-Time

In Cooperation with Bayreuth Hospital

Publications

  • Kage, A.; Mühldorfer, S.; Bergen, T.; Münzenmayer, C.; Wittenberg, T.: The importance of image quality assessment for the creation of reference image collection for computer-assisted diagnosis
in colonoscopy. In: Int J CARS (2013) 8 (Suppl 1): pp. 405-406, Heidelberg, 2013.
  • Kage, A.; Mühldorfer, S.; Münzenmayer, C.; Witten­berg, T.. Computer-Assistierte Detektion von Polypen in der Kolonoskopie. In: Endos­kopie Heute, Ausgabe 26(1), 2013. DOI: 10.1055/s-0033-1333994.
  • Münzenmayer, C.; Mühldorfer, S.; Engelhardt, L.; Benz, M.; Wittenberg, T.: Bildbasierte Unterscheidung kolorektaler Polypen und Hintergrundgewebe mittels Farbtexturanalyse. In: Endoskopie Heute, 24(1), S. 60, 2011.
  • Münzenmayer, C.;  Shevchenko, N.; Mühldorfer, S.; Wittenberg, T.. Unser´s statistical features versus color and position for automated polyp recognition. In: Int. J. Comput. Assist. Radiol. Surg. (CARS), 2009.
  • Ameling, S.; Wirth, S.; Shevchenko, N.; Wittenberg, T.; Paulus, D.; Münzenmayer, C.: Detection of lesions in colonoscopic images: A review. In: Dössel O.; Schlegel, W. C. (Eds.); Proc´s World Congress on Me­di­cal Physics & Biomed. Eng. 2009, Vol. 25/IV of IFMBE Proc's, pp. 995–998. 7.-12.9. 2009, Munich.
  • Shevchenko, N.; Mühldorfer, S.; Wittenberg, T.; Münzenmayer, C.: Untersuchung von Texturanalyse­me­tho­den zur automatischen Polypenerkennung. In: Bartz, D; et al (Eds.);  Proc´s Computer- und Roboter­assis­tierte Chirurgie (CURAC), pp. 205-206. 7. Jahrest. der CURAC, 24.-26.9.2008 in Leipzig, 2008.

More Information

 

Your Development Partner for Medical Image Analysis

Talk to us – together we will find a solution for your medical image processing challenge:  -> Please send an email if you are interested

Software based Image Analysis and Enhancement

Our focus are the domains of Microscopy and Endoscopy.