Mohammad Ali Armin1,2, Girija Chetty3, Hans De Visser4, Cedric Dumas4, Florian Grimpen5, Olivier Salvado6. 1. HCT, University of Canberra, Bruce, Canberra, ACT, Australia. m.a.armin@gmail.com. 2. CSIRO Biomedical Informatics, The Australian e-Health Research Centre, Level 5, UQ Health Sciences, Brisbane, QLD, 4029, Australia. m.a.armin@gmail.com. 3. HCT, University of Canberra, Bruce, Canberra, ACT, Australia. 4. CSIRO Biomedical Informatics, The Australian e-Health Research Centre, Level 5, UQ Health Sciences, Brisbane, QLD, 4029, Australia. 5. Department of Gastroenterology and Hepatology, Royal Brisbane and Women's Hospital, Herston, Brisbane, QLD, Australia. 6. CSIRO Biomedical Informatics, The Australian e-Health Research Centre, Level 5, UQ Health Sciences, Brisbane, QLD, 4029, Australia. Olivier.Salvado@csiro.au.
Abstract
PURPOSE: Optical colonoscopy is a prominent procedure by which clinicians examine the surface of the colon for cancerous polyps using a flexible colonoscope. One of the main concerns regarding the quality of the colonoscopy is to ensure that the whole colonic surface has been inspected for abnormalities. In this paper, we aim at estimating areas that have not been covered thoroughly by providing a map from the internal colon surface. METHODS: Camera parameters were estimated using optical flow between consecutive colonoscopy frames. A cylinder model was fitted to the colon structure using 3D pseudo stereo vision and projected into each frame. A circumferential band from the cylinder was extracted to unroll the internal colon surface (band image). By registering these band images, drift in estimating camera motion could be reduced, and a visibility map of the colon surface could be generated, revealing uncovered areas by the colonoscope. Hidden areas behind haustral folds were ignored in this study. The method was validated on simulated and actual colonoscopy videos. The realistic simulated videos were generated using a colonoscopy simulator with known ground truth, and the actual colonoscopy videos were manually assessed by a clinical expert. RESULTS: The proposed method obtained a sensitivity and precision of 98 and 96 % for detecting the number of uncovered areas on simulated data, whereas validation on real videos showed a sensitivity and precision of 96 and 78 %, respectively. Error in camera motion drift could be reduced by almost 50 % using results from band image registration. CONCLUSION: Using a simple cylindrical model for the colon and reducing drift by registering band images allows for the generation of visibility maps. The current results also suggest that the provided feedback through the visibility map could enhance clinicians' awareness of uncovered areas, which in return could reduce the probability of missing polyps.
PURPOSE: Optical colonoscopy is a prominent procedure by which clinicians examine the surface of the colon for cancerous polyps using a flexible colonoscope. One of the main concerns regarding the quality of the colonoscopy is to ensure that the whole colonic surface has been inspected for abnormalities. In this paper, we aim at estimating areas that have not been covered thoroughly by providing a map from the internal colon surface. METHODS: Camera parameters were estimated using optical flow between consecutive colonoscopy frames. A cylinder model was fitted to the colon structure using 3D pseudo stereo vision and projected into each frame. A circumferential band from the cylinder was extracted to unroll the internal colon surface (band image). By registering these band images, drift in estimating camera motion could be reduced, and a visibility map of the colon surface could be generated, revealing uncovered areas by the colonoscope. Hidden areas behind haustral folds were ignored in this study. The method was validated on simulated and actual colonoscopy videos. The realistic simulated videos were generated using a colonoscopy simulator with known ground truth, and the actual colonoscopy videos were manually assessed by a clinical expert. RESULTS: The proposed method obtained a sensitivity and precision of 98 and 96 % for detecting the number of uncovered areas on simulated data, whereas validation on real videos showed a sensitivity and precision of 96 and 78 %, respectively. Error in camera motion drift could be reduced by almost 50 % using results from band image registration. CONCLUSION: Using a simple cylindrical model for the colon and reducing drift by registering band images allows for the generation of visibility maps. The current results also suggest that the provided feedback through the visibility map could enhance clinicians' awareness of uncovered areas, which in return could reduce the probability of missing polyps.
Entities:
Keywords:
Camera motion drift; Camera motion parameters; Colonoscopy quality; Optical colonoscopy; Uncovered area; Visibility map
Authors: K Mori; D Deguchi; J Sugiyama; Y Suenaga; J Toriwaki; C R Maurer; H Takabatake; H Natori Journal: Med Image Anal Date: 2002-09 Impact factor: 8.545
Authors: Vani Konda; Shailendra S Chauhan; Barham K Abu Dayyeh; Joo Ha Hwang; Sri Komanduri; Michael A Manfredi; John T Maple; Faris M Murad; Uzma D Siddiqui; Subhas Banerjee Journal: Gastrointest Endosc Date: 2015-03-06 Impact factor: 9.427