Computer Graphics and Visualization › Publications › Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography

In Proceedings of ISBI

Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography

V.F. van Ravesteijn, Lingxiao Zhao, Charl P. Botha, Frits H. Post, F.M. Vos, and L.J. van Vliet

(a) A polyp with its surrounding environment. (b) Example of the curvature streamlines generated in the vicinity of the polyp.

Publisher Paper Cite More

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 lowcomplex 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.

More Information

Publisher Paper preprint

Citation

V.F. van Ravesteijn, Lingxiao Zhao, Charl P. Botha, Frits H. Post, F.M. Vos, and L.J. van Vliet, Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography, In Proceedings of ISBI, pp. 907–910, 2009.

BibTex 

@inproceedings{bib:van ravesteijn:2009,
    author       = { van Ravesteijn, V.F. and Zhao, Lingxiao and Botha, Charl P. and Post, Frits H. and Vos, F.M. and van Vliet, L.J. },    
    title        = { Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography },
    booktitle    = { In Proceedings of ISBI },
    year         = { 2009 },
    pages        = { 907--910 },
    doi          = { 10.1109/ISBI.2009.5193200 },
    dblp         = { conf/isbi/RavesteijnZBPVV09 },
    url          = { https://publications.graphics.tudelft.nl/papers/367 },
}