Assessment of an optical flow field-based polyp detector for CT colonography

B. Acar, C. F. Beaulieu, D. S. Paik, S. B. Göktürk, C. Tomasi, Judy Yee, S. Napel

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Most current computer-aided detection (CAD) algorithms for the fully automatic detection of colonic polyps from 3D CT data suffer from high false positive rates. We developed and evaluated a post-processing algorithm to decrease the false positive rate of such a method. Our method attempts to model the way a radiologist recognizes a polyp while scrolling a cross-sectional plane through 3D CT data by quantifying the change in location of the edges in 2D plane. It uses a classifier for identification based on the Mahalanobis distance. The new method increased the ROC curve area from 0.89 to 0.98 (an increase from 34.5% to 85.0% in specificity for 100% sensitivity) in a population of 8 patients.

Original languageEnglish (US)
Pages (from-to)2774-2777
Number of pages4
JournalAnnual Reports of the Research Reactor Institute, Kyoto University
Volume3
StatePublished - Dec 1 2001
Externally publishedYes

Fingerprint

Optical flows
Flow fields
Detectors
Classifiers
Processing

Keywords

  • CAD
  • Computed tomographic colonography
  • Optical flow fields
  • Polyp detection
  • Virtual colonoscopy

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Mechanical Engineering

Cite this

Acar, B., Beaulieu, C. F., Paik, D. S., Göktürk, S. B., Tomasi, C., Yee, J., & Napel, S. (2001). Assessment of an optical flow field-based polyp detector for CT colonography. Annual Reports of the Research Reactor Institute, Kyoto University, 3, 2774-2777.

Assessment of an optical flow field-based polyp detector for CT colonography. / Acar, B.; Beaulieu, C. F.; Paik, D. S.; Göktürk, S. B.; Tomasi, C.; Yee, Judy; Napel, S.

In: Annual Reports of the Research Reactor Institute, Kyoto University, Vol. 3, 01.12.2001, p. 2774-2777.

Research output: Contribution to journalArticle

Acar, B, Beaulieu, CF, Paik, DS, Göktürk, SB, Tomasi, C, Yee, J & Napel, S 2001, 'Assessment of an optical flow field-based polyp detector for CT colonography', Annual Reports of the Research Reactor Institute, Kyoto University, vol. 3, pp. 2774-2777.
Acar, B. ; Beaulieu, C. F. ; Paik, D. S. ; Göktürk, S. B. ; Tomasi, C. ; Yee, Judy ; Napel, S. / Assessment of an optical flow field-based polyp detector for CT colonography. In: Annual Reports of the Research Reactor Institute, Kyoto University. 2001 ; Vol. 3. pp. 2774-2777.
@article{97819adb85ad4e448cd8b2ed0adbd9e0,
title = "Assessment of an optical flow field-based polyp detector for CT colonography",
abstract = "Most current computer-aided detection (CAD) algorithms for the fully automatic detection of colonic polyps from 3D CT data suffer from high false positive rates. We developed and evaluated a post-processing algorithm to decrease the false positive rate of such a method. Our method attempts to model the way a radiologist recognizes a polyp while scrolling a cross-sectional plane through 3D CT data by quantifying the change in location of the edges in 2D plane. It uses a classifier for identification based on the Mahalanobis distance. The new method increased the ROC curve area from 0.89 to 0.98 (an increase from 34.5{\%} to 85.0{\%} in specificity for 100{\%} sensitivity) in a population of 8 patients.",
keywords = "CAD, Computed tomographic colonography, Optical flow fields, Polyp detection, Virtual colonoscopy",
author = "B. Acar and Beaulieu, {C. F.} and Paik, {D. S.} and G{\"o}kt{\"u}rk, {S. B.} and C. Tomasi and Judy Yee and S. Napel",
year = "2001",
month = "12",
day = "1",
language = "English (US)",
volume = "3",
pages = "2774--2777",
journal = "Annual Reports of the Research Reactor Institute, Kyoto University",
issn = "0454-9244",

}

TY - JOUR

T1 - Assessment of an optical flow field-based polyp detector for CT colonography

AU - Acar, B.

AU - Beaulieu, C. F.

AU - Paik, D. S.

AU - Göktürk, S. B.

AU - Tomasi, C.

AU - Yee, Judy

AU - Napel, S.

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Most current computer-aided detection (CAD) algorithms for the fully automatic detection of colonic polyps from 3D CT data suffer from high false positive rates. We developed and evaluated a post-processing algorithm to decrease the false positive rate of such a method. Our method attempts to model the way a radiologist recognizes a polyp while scrolling a cross-sectional plane through 3D CT data by quantifying the change in location of the edges in 2D plane. It uses a classifier for identification based on the Mahalanobis distance. The new method increased the ROC curve area from 0.89 to 0.98 (an increase from 34.5% to 85.0% in specificity for 100% sensitivity) in a population of 8 patients.

AB - Most current computer-aided detection (CAD) algorithms for the fully automatic detection of colonic polyps from 3D CT data suffer from high false positive rates. We developed and evaluated a post-processing algorithm to decrease the false positive rate of such a method. Our method attempts to model the way a radiologist recognizes a polyp while scrolling a cross-sectional plane through 3D CT data by quantifying the change in location of the edges in 2D plane. It uses a classifier for identification based on the Mahalanobis distance. The new method increased the ROC curve area from 0.89 to 0.98 (an increase from 34.5% to 85.0% in specificity for 100% sensitivity) in a population of 8 patients.

KW - CAD

KW - Computed tomographic colonography

KW - Optical flow fields

KW - Polyp detection

KW - Virtual colonoscopy

UR - http://www.scopus.com/inward/record.url?scp=0035781905&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035781905&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0035781905

VL - 3

SP - 2774

EP - 2777

JO - Annual Reports of the Research Reactor Institute, Kyoto University

JF - Annual Reports of the Research Reactor Institute, Kyoto University

SN - 0454-9244

ER -