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

Vincent van Ravesteijn; Lingxiao Zhao; Charl Botha; Frits Post; Frans Vos; Lucas van Vliet

doi:10.1109/ISBI.2009.5193200

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

Vincent van Ravesteijn
, Lingxiao Zhao
, Charl Botha
, Frits Post
, Frans Vos
, Lucas van Vliet^*

^*Corresponding author for this work

School of AI and Advanced Computing

Delft University of Technology

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

5 Citations (Scopus)

1 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Place of Publication	Boston, MA, USA
Publisher	IEEE Computer Society
Pages	907-910
Number of pages	4
ISBN (Electronic)	978-1-4244-3932-4
ISBN (Print)	978-1-4244-3931-7
DOIs	https://doi.org/10.1109/ISBI.2009.5193200
Publication status	Published - 28 Jun 2009

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/ISBI.2009.5193200Licence: Unspecified

ISBI2009Licence: Unspecified

Cite this

@inproceedings{e40713d0cbc84e9f917c45f35e0e885a,

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

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.",

author = "\{van Ravesteijn\}, Vincent and Lingxiao Zhao and Charl Botha and Frits Post and Frans Vos and \{van Vliet\}, Lucas",

year = "2009",

month = jun,

day = "28",

doi = "10.1109/ISBI.2009.5193200",

language = "English",

isbn = "978-1-4244-3931-7",

pages = "907--910",

booktitle = "Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro",

publisher = "IEEE Computer Society",

}

Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography. / van Ravesteijn, Vincent; Zhao, Lingxiao; Botha, Charl et al.
Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. Boston, MA, USA: IEEE Computer Society, 2009. p. 907-910.

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Combining Mesh, Volume, and Streamline Representations for Polyp Detection in CT Colonography

AU - van Ravesteijn, Vincent

AU - Zhao, Lingxiao

AU - Botha, Charl

AU - Post, Frits

AU - Vos, Frans

AU - van Vliet, Lucas

PY - 2009/6/28

Y1 - 2009/6/28

N2 - 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.

AB - 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.

U2 - 10.1109/ISBI.2009.5193200

DO - 10.1109/ISBI.2009.5193200

M3 - Conference Proceeding

SN - 978-1-4244-3931-7

SP - 907

EP - 910

BT - Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

PB - IEEE Computer Society

CY - Boston, MA, USA

ER -

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

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this