Improved Colon Navigation for Efficient Polyp Detection in Virtual Colonoscopy

Colon cancer is a leading cause of death in the world and its early diagnosis highly increases the chances of survival. Virtual colonoscopy is a widely spreading technology that is used for polyp detection, the primary cause of colon cancer. This paper revisits an existing virtual colonoscopy technique, called Fly-over. It splits the colon into two halves along its centerline and assigns a camera to each half for navigation. While cutting the colon along its centerline increases the possibility of having missed polyps, the technique is re-visited here and the cutting framework is changed, which improved the rate of detection. Clinical validation was assessed by testing the navigation technique on several cases of real and synthetic challenging polyps versus other techniques. Fly-over technique provides efficient polyp detection of up to 100% with the least distortion rate.

[1]  Beom Jin Park,et al.  Panoramic endoluminal display with minimal image distortion using circumferential radial ray-casting for primary three-dimensional interpretation of CT colonography , 2009, European Radiology.

[2]  Aly A. Farag,et al.  Accurate Tracking of Monotonically Advancing Fronts , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  M. Ismail,et al.  3D automated colon segmentation for efficient polyp detection , 2012, 2012 Cairo International Biomedical Engineering Conference (CIBEC).

[4]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[5]  Aly A. Farag,et al.  Virtual Fly-Over: A New Visualization Technique for Virtual Colonoscopy , 2006, MICCAI.

[6]  Kaleem Siddiqi,et al.  Flux driven fly throughs , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[7]  Feng Qiu,et al.  Conformal virtual colon flattening , 2006, SPM '06.

[8]  P. Pickhardt,et al.  Surface visualization at 3D endoluminal CT colonography: degree of coverage and implications for polyp detection. , 2006, Gastroenterology.

[9]  Aly A. Farag,et al.  Fully automated 3D colon segmentation for early detection of colorectal cancer based on convex formulation of the active contour model , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[10]  Lasse Riis Østergaard,et al.  Active Surface Approach for Extraction of the Human Cerebral Cortex from MRI , 2006, MICCAI.