CAD of colon cancer on CT colonography cases without cathartic bowel preparation

Marius George Linguraru, Shan Zhao, Robert L. Van Uitert, Jiamin Liu, Joel Garland Fletcher, Armando Manduca, Ronald M. Summers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Computer-aided diagnosis (CAD) systems must show sufficient versatility to produce robust analysis on a large variety of data. In the case of colonography, CAD has not been designed to cope with the presence of stool, although labeling the stool with high contrast agents replaces the use of laxatives and reduces the patient discomfort. This procedure introduces additional challenges for the diagnosis, such as poorly tagged stool, stool sticking to colonic walls, and heterogeneous stool (tagged stool mixed with air or untagged stool). Our study proposes a robust algorithm for heterogeneous stool removal to be employed as a preprocessing module for CAD systems in colonic cancer detection. Colonoscopy data are automatically cleansed of residual stool to enhance the polyp appearance for improved diagnosis. The algorithm uses expectationmaximization, quadratic regression, level sets and minimum variance. Results show stool removal accuracy on polyps which are partially or fully covered by stool. The results are robust on stool lining and large pools of heterogeneous and weakly-tagged stool. The automatic detection of colon polyps using our CAD system on cathartic-free data improves considerably with the addition of the automatic stool removal module from 74% to 86% true positive (TP) rate at 6.4 false positives (FP)/case.

Original languageEnglish (US)
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"
Pages2996-2999
Number of pages4
StatePublished - 2008
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: Aug 20 2008Aug 25 2008

Other

Other30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period8/20/088/25/08

Fingerprint

Cathartics
Computed Tomographic Colonography
Computer aided diagnosis
Colonic Neoplasms
Polyps
Linings
Labeling
Laxatives
Colonoscopy
Contrast Media
Colon
Air

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Linguraru, M. G., Zhao, S., Van Uitert, R. L., Liu, J., Fletcher, J. G., Manduca, A., & Summers, R. M. (2008). CAD of colon cancer on CT colonography cases without cathartic bowel preparation. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology" (pp. 2996-2999). [4649833]

CAD of colon cancer on CT colonography cases without cathartic bowel preparation. / Linguraru, Marius George; Zhao, Shan; Van Uitert, Robert L.; Liu, Jiamin; Fletcher, Joel Garland; Manduca, Armando; Summers, Ronald M.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. p. 2996-2999 4649833.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Linguraru, MG, Zhao, S, Van Uitert, RL, Liu, J, Fletcher, JG, Manduca, A & Summers, RM 2008, CAD of colon cancer on CT colonography cases without cathartic bowel preparation. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"., 4649833, pp. 2996-2999, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 8/20/08.
Linguraru MG, Zhao S, Van Uitert RL, Liu J, Fletcher JG, Manduca A et al. CAD of colon cancer on CT colonography cases without cathartic bowel preparation. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. p. 2996-2999. 4649833
Linguraru, Marius George ; Zhao, Shan ; Van Uitert, Robert L. ; Liu, Jiamin ; Fletcher, Joel Garland ; Manduca, Armando ; Summers, Ronald M. / CAD of colon cancer on CT colonography cases without cathartic bowel preparation. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. pp. 2996-2999
@inproceedings{6bae8a64baf148ffa6c5bd44080d7677,
title = "CAD of colon cancer on CT colonography cases without cathartic bowel preparation",
abstract = "Computer-aided diagnosis (CAD) systems must show sufficient versatility to produce robust analysis on a large variety of data. In the case of colonography, CAD has not been designed to cope with the presence of stool, although labeling the stool with high contrast agents replaces the use of laxatives and reduces the patient discomfort. This procedure introduces additional challenges for the diagnosis, such as poorly tagged stool, stool sticking to colonic walls, and heterogeneous stool (tagged stool mixed with air or untagged stool). Our study proposes a robust algorithm for heterogeneous stool removal to be employed as a preprocessing module for CAD systems in colonic cancer detection. Colonoscopy data are automatically cleansed of residual stool to enhance the polyp appearance for improved diagnosis. The algorithm uses expectationmaximization, quadratic regression, level sets and minimum variance. Results show stool removal accuracy on polyps which are partially or fully covered by stool. The results are robust on stool lining and large pools of heterogeneous and weakly-tagged stool. The automatic detection of colon polyps using our CAD system on cathartic-free data improves considerably with the addition of the automatic stool removal module from 74{\%} to 86{\%} true positive (TP) rate at 6.4 false positives (FP)/case.",
author = "Linguraru, {Marius George} and Shan Zhao and {Van Uitert}, {Robert L.} and Jiamin Liu and Fletcher, {Joel Garland} and Armando Manduca and Summers, {Ronald M.}",
year = "2008",
language = "English (US)",
isbn = "9781424418152",
pages = "2996--2999",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - {"}Personalized Healthcare through Technology{"}",

}

TY - GEN

T1 - CAD of colon cancer on CT colonography cases without cathartic bowel preparation

AU - Linguraru, Marius George

AU - Zhao, Shan

AU - Van Uitert, Robert L.

AU - Liu, Jiamin

AU - Fletcher, Joel Garland

AU - Manduca, Armando

AU - Summers, Ronald M.

PY - 2008

Y1 - 2008

N2 - Computer-aided diagnosis (CAD) systems must show sufficient versatility to produce robust analysis on a large variety of data. In the case of colonography, CAD has not been designed to cope with the presence of stool, although labeling the stool with high contrast agents replaces the use of laxatives and reduces the patient discomfort. This procedure introduces additional challenges for the diagnosis, such as poorly tagged stool, stool sticking to colonic walls, and heterogeneous stool (tagged stool mixed with air or untagged stool). Our study proposes a robust algorithm for heterogeneous stool removal to be employed as a preprocessing module for CAD systems in colonic cancer detection. Colonoscopy data are automatically cleansed of residual stool to enhance the polyp appearance for improved diagnosis. The algorithm uses expectationmaximization, quadratic regression, level sets and minimum variance. Results show stool removal accuracy on polyps which are partially or fully covered by stool. The results are robust on stool lining and large pools of heterogeneous and weakly-tagged stool. The automatic detection of colon polyps using our CAD system on cathartic-free data improves considerably with the addition of the automatic stool removal module from 74% to 86% true positive (TP) rate at 6.4 false positives (FP)/case.

AB - Computer-aided diagnosis (CAD) systems must show sufficient versatility to produce robust analysis on a large variety of data. In the case of colonography, CAD has not been designed to cope with the presence of stool, although labeling the stool with high contrast agents replaces the use of laxatives and reduces the patient discomfort. This procedure introduces additional challenges for the diagnosis, such as poorly tagged stool, stool sticking to colonic walls, and heterogeneous stool (tagged stool mixed with air or untagged stool). Our study proposes a robust algorithm for heterogeneous stool removal to be employed as a preprocessing module for CAD systems in colonic cancer detection. Colonoscopy data are automatically cleansed of residual stool to enhance the polyp appearance for improved diagnosis. The algorithm uses expectationmaximization, quadratic regression, level sets and minimum variance. Results show stool removal accuracy on polyps which are partially or fully covered by stool. The results are robust on stool lining and large pools of heterogeneous and weakly-tagged stool. The automatic detection of colon polyps using our CAD system on cathartic-free data improves considerably with the addition of the automatic stool removal module from 74% to 86% true positive (TP) rate at 6.4 false positives (FP)/case.

UR - http://www.scopus.com/inward/record.url?scp=61849104156&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849104156&partnerID=8YFLogxK

M3 - Conference contribution

C2 - 19163336

AN - SCOPUS:61849104156

SN - 9781424418152

SP - 2996

EP - 2999

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"

ER -