Detecting polyps and lesions during colonoscopies

Left image: polyps annotated by experts; right image: polyps detected by AI
  • Colorectal cancer is the second most common cause of death from cancer for men and women alike.
  • In most cases, colonic polyps are symptomatic of the early stages of colorectal cancer.
  • Regular screening helps detect polyps at an early stage and thus prevent this type of cancer from developing.



Such polyps, however, are often missed during colonoscopies. Small polyps and flat new polyp formations that are deeply embedded are especially difficult to detect. And the physician’s experience and level of attention can also influence the detection rate.


Automatically detect and highlight polyps in the endoscope’s live video signal.  

The future of colonoscopy: AI-based polyp detection


Increase polyp detection sensitivity and specificity using artificial intelligence.


Current status

  • Built Multi-center, multi endoscope database
    •     “Bayreuth” DB: 2484 640 x 504 HD (no open access database!)
    •     Public dataset CVC-ClinicDB: 612 388 x 284 SD
    •     Public dataset ETIS-LaribPolypDB: 194 1225 x 966 HD
  • Trained Deep Neural Network to detect and outline polyps
  • Results for above datasets: recall of 83-92% and precision of 74-86%
  • Looking for commercialization partners



Zobel et al, Computer Aided Detection of Polyps in Whitelight-Colonoscopy Images using Deep Neural Networks , Current Directions in Biomedical Engineering 2018;4(1)

Privacy warning

With the click on the play button an external video from is loaded and started. Your data is possible transferred and stored to third party. Do not start the video if you disagree. Find more about the youtube privacy statement under the following link:

AI-free real-time detection

  • In 2017, our AI-free real-time detection software was used in a prospective study at the Klinikum rechts der Isar of the Technical University of Munich
  • Results        
    • The detection system was applied in 55 routine colonoscopies free of any complications
    • Our algorithm has detected 55 out of 73 (75%). All polyps exceeding 7mm have been correctly detected  
  • Conclusion
    • Computer-assisted automated low-delay polyp detection is feasible during real-time colonoscopy
    • The detection rate with respect to smaller and flat shaped polyps is currently being improved


Further information: Kolopol Research Project (finished)



Gastrointest Endosc. 2019 Mar;89(3):576-582.e1. doi: 10.1016/j.gie.2018.09.042 Epub 2018 Oct 17,
Klare et al., Automated polyp detection in the colorectum: a prospective study (with videos).

More Information


Engineering. Imaging. Sensors. Analysis.

Current and finished Products and Projects

Development partner for personalized medical engineering

Research and development services from a single source