Combining mesh, volume, and streamline representations for polyp detection in CT colonography

Authors:
V. F. Van Ravesteijn;L. Zhao;C. P. Botha;F. H. Post;F. M. Vos;L. J. Van Vliet
Affiliations:
Quantitative Imaging Group, Faculty of Applied Sciences;Computer Graphics & CAD/CAM Group, Faculty of EEMCS, Delft University of Technology, The Netherlands;Computer Graphics & CAD/CAM Group, Faculty of EEMCS, Delft University of Technology, The Netherlands;Computer Graphics & CAD/CAM Group, Faculty of EEMCS, Delft University of Technology, The Netherlands;Quantitative Imaging Group, Faculty of Applied Sciences and Academic Medical Center, Amsterdam, The Netherlands;Quantitative Imaging Group, Faculty of Applied Sciences
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 4
Cited 1

Lines of Curvature for Polyp Detection in Virtual Colonoscopy

IEEE Transactions on Visualization and Computer Graphics
Segmentation and size measurement of polyps in CT colonography

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Symmetric curvature patterns for colonic polyp detection

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II
Detection of protrusions in curved folded surfaces applied to automated polyp detection in CT colonography

MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part II

Conformal geometry based supine and prone colon registration

MICCAI'10 Proceedings of the Second international conference on Virtual Colonoscopy and Abdominal Imaging: computational challenges and clinical opportunities

Quantified Score

Hi-index	0.00

Visualization

Abstract

CT colonography is a screening technique for adenomatous colorectal polyps, which are important precursors to colon cancer. Computer aided detection (CAD) systems are developed to assist radiologists. We present a CAD system that substantially reduces false positives while keeping the sensitivity high. Hereto, we combine protrusion measures derived from the solution of a non-linear partial differential equation (PDE) applied to both an explicit mesh and an implicit volumetric representation of the colon wall. The shape of the protruding elements is efficiently described via a technique from data visualization based on curvature streamlines. A low-complex pattern recognition system based on an intuitive feature from the aforementioned representations improves performance to less than 1.6 false positives per scan at 92% sensitivity per polyp.