Surgical Assistance

Automated visibility map from colonoscopy video to support clinical diagnosis and improve the quality of colonoscopy

Problem:
Colorectal cancer is one of the leading causes of cancer related death in Australia and the world. When diagnosed early, survival from cancerous polyps can increase up to 90%. Among screening methods, optical colonoscopy is widely used to diagnose and remove cancerous polyps. Although optical colonoscopy is an effective procedure for diagnosing colorectal cancer, there are many factors that affect the quality of this intervention. Inspecting the whole colonic surface in order to detect polyps and other lesions is challenging because haustral folds can hide lesions, the organ might deform, visibility can be reduced due to dirty lens, and also because challenges in operating the colonoscope could result in not visualising all the colon surface. An undesirable consequence is missing cancerous lesions, up to 33% according to recent publications.

Our Solution:
We have developed an assistive technology to improve the quality of the colonoscopy. From the colonoscopy video a panoramic view of internal colon surface is automatically created (visibility map). We tested and validated this technology on our colonoscopy simulator and real colonoscopy videos.

 

Our results showed that this method could reduce the number of uncovered areas by identifying them on the visibility map. In the future we aim at developing real-time assistive application to help reduce colorectal cancer.

 

Figure 1 The first row is simulated colon generated by state of the art CSIRO simulator, the second is the ground truth showing uncovered areas as black area when camera arbitrary moved inside the colon, and the last row is a visibility map generated by our method.

Figure 1 The first row is simulated colon generated by state of the art CSIRO simulator, the second is the ground truth showing uncovered areas as black area when camera arbitrary moved inside the colon, and the last row is a visibility map generated by our method.

Benefits of a visibility map

  • Help to inspect all areas (reduce missed lesions)
  • Generate a report (help in following up patients)
  • Help navigation (reduce intervention time)
  • Quantitative feedback (can be used as an educational tool)

Generating a visibility map from internal colon surface

 Publications

  • Patent pending to cover aspects of the technologies.
  • M. A. Armin, H. De Visser, G. Chetty, C. Dumas, D. Conlan, F. Grimpen, and O. Salvado, “Visibility Map: A New Method in Evaluation Quality of Optical Colonoscopy,” in MICCAI 2015, vol. 9349, N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, Eds. Cham: Springer International Publishing, 2015, pp. 396–404. (http://link.springer.com/chapter/10.1007%2F978-3-319-24553-9_49#page-1)
  • M. A. Armin, G. Chetty, F. Jurgen, HD. Visser, C. Dumas, A. Fazlollahi, F. Grimpen, O. Salvado, “Uninformative frame detection in colonoscopy through motion, edge and Colour Features”. International workshop on computer -assisted and robotic in MICCAI 2015, pp. 153-162. (http://link.springer.com/chapter/10.1007%2F978-3-319-29965-5_15)
  • M. A. Armin, G. Chetty, H. De Visser, C. Dumas, F. Grimpen, and O. Salvado, “Automated Visibility Map of the Internal Colon Surface from Colonoscopy Video”, International Journal of Computer Assisted Radiology and Surgery (IJCARS), under review