Automated polyp detection at CT colonography: Feasibility assessment in a human population

R. M. Summers, C. Daniel Johnson, L. M. Pusanik, J. D. Malley, A. M. Youssef, J. E. Reed

Research output: Contribution to journalArticle

227 Citations (Scopus)

Abstract

PURPOSE: To test the feasibility of and improve a computer algorithm to automatically detect colonic polyps in real human computed tomographic (CT) colonographic data sets. MATERIALS AND METHODS: Twenty patients with known polyps underwent CT colonography in the supine position. CT colonographic data were processed by using a shape-based algorithm that depicts masses that protrude into the lumen. We studied nine shape criteria and three isosurface threshold settings. Results were compared with those of conventional colonoscopy performed the same day. RESULTS: There were 50 polyps (28 were ≥10 mm in size; 12, 5-9 mm; 10, <5 mm). The sensitivity with optimal settings for detecting polyps 10 mm or greater was 64% (18 of 28). Sensitivity improved to 71% (10 of 14) for polyps 10 mm or greater in well-distended colonic segments. Performance decreased for polyps less than 10 mm, poorly distended colonic segments, and other shape algorithms. There was a mean of six false-positive lesion sites per colon. These sites were reduced 39% to 3.5 per colon by sampling CT attenuation at the lesion site and discarding sites having attenuation less than a threshold. CONCLUSION: Automated detection of colonic polyps, especially clinically important large polyps, is feasible. Colonic distention is an important determinant of sensitivity. Further increases in sensitivity may be achieved by adding prone CT colonography.

Original languageEnglish (US)
Pages (from-to)51-59
Number of pages9
JournalRadiology
Volume219
Issue number1
DOIs
StatePublished - Jan 1 2001
Externally publishedYes

Fingerprint

Computed Tomographic Colonography
Polyps
Colonic Polyps
Population
Colon
Supine Position
Colonoscopy

Keywords

  • Colon neoplasms, diagnosis, 75.12115, 75.12119, 75.1282, 75.311
  • Colon, CT, 75.12115, 75.12119, 75.1282
  • Computed tomography (CT)
  • Computed tomography (CT), Computer programs
  • Computed tomography (CT), Image processing
  • Three-dimensional, 75.12117

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Automated polyp detection at CT colonography : Feasibility assessment in a human population. / Summers, R. M.; Johnson, C. Daniel; Pusanik, L. M.; Malley, J. D.; Youssef, A. M.; Reed, J. E.

In: Radiology, Vol. 219, No. 1, 01.01.2001, p. 51-59.

Research output: Contribution to journalArticle

Summers, R. M. ; Johnson, C. Daniel ; Pusanik, L. M. ; Malley, J. D. ; Youssef, A. M. ; Reed, J. E. / Automated polyp detection at CT colonography : Feasibility assessment in a human population. In: Radiology. 2001 ; Vol. 219, No. 1. pp. 51-59.
@article{1d8f11720a2548f49d682ab206b04529,
title = "Automated polyp detection at CT colonography: Feasibility assessment in a human population",
abstract = "PURPOSE: To test the feasibility of and improve a computer algorithm to automatically detect colonic polyps in real human computed tomographic (CT) colonographic data sets. MATERIALS AND METHODS: Twenty patients with known polyps underwent CT colonography in the supine position. CT colonographic data were processed by using a shape-based algorithm that depicts masses that protrude into the lumen. We studied nine shape criteria and three isosurface threshold settings. Results were compared with those of conventional colonoscopy performed the same day. RESULTS: There were 50 polyps (28 were ≥10 mm in size; 12, 5-9 mm; 10, <5 mm). The sensitivity with optimal settings for detecting polyps 10 mm or greater was 64{\%} (18 of 28). Sensitivity improved to 71{\%} (10 of 14) for polyps 10 mm or greater in well-distended colonic segments. Performance decreased for polyps less than 10 mm, poorly distended colonic segments, and other shape algorithms. There was a mean of six false-positive lesion sites per colon. These sites were reduced 39{\%} to 3.5 per colon by sampling CT attenuation at the lesion site and discarding sites having attenuation less than a threshold. CONCLUSION: Automated detection of colonic polyps, especially clinically important large polyps, is feasible. Colonic distention is an important determinant of sensitivity. Further increases in sensitivity may be achieved by adding prone CT colonography.",
keywords = "Colon neoplasms, diagnosis, 75.12115, 75.12119, 75.1282, 75.311, Colon, CT, 75.12115, 75.12119, 75.1282, Computed tomography (CT), Computed tomography (CT), Computer programs, Computed tomography (CT), Image processing, Three-dimensional, 75.12117",
author = "Summers, {R. M.} and Johnson, {C. Daniel} and Pusanik, {L. M.} and Malley, {J. D.} and Youssef, {A. M.} and Reed, {J. E.}",
year = "2001",
month = "1",
day = "1",
doi = "10.1148/radiology.219.1.r01ap0751",
language = "English (US)",
volume = "219",
pages = "51--59",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "1",

}

TY - JOUR

T1 - Automated polyp detection at CT colonography

T2 - Feasibility assessment in a human population

AU - Summers, R. M.

AU - Johnson, C. Daniel

AU - Pusanik, L. M.

AU - Malley, J. D.

AU - Youssef, A. M.

AU - Reed, J. E.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - PURPOSE: To test the feasibility of and improve a computer algorithm to automatically detect colonic polyps in real human computed tomographic (CT) colonographic data sets. MATERIALS AND METHODS: Twenty patients with known polyps underwent CT colonography in the supine position. CT colonographic data were processed by using a shape-based algorithm that depicts masses that protrude into the lumen. We studied nine shape criteria and three isosurface threshold settings. Results were compared with those of conventional colonoscopy performed the same day. RESULTS: There were 50 polyps (28 were ≥10 mm in size; 12, 5-9 mm; 10, <5 mm). The sensitivity with optimal settings for detecting polyps 10 mm or greater was 64% (18 of 28). Sensitivity improved to 71% (10 of 14) for polyps 10 mm or greater in well-distended colonic segments. Performance decreased for polyps less than 10 mm, poorly distended colonic segments, and other shape algorithms. There was a mean of six false-positive lesion sites per colon. These sites were reduced 39% to 3.5 per colon by sampling CT attenuation at the lesion site and discarding sites having attenuation less than a threshold. CONCLUSION: Automated detection of colonic polyps, especially clinically important large polyps, is feasible. Colonic distention is an important determinant of sensitivity. Further increases in sensitivity may be achieved by adding prone CT colonography.

AB - PURPOSE: To test the feasibility of and improve a computer algorithm to automatically detect colonic polyps in real human computed tomographic (CT) colonographic data sets. MATERIALS AND METHODS: Twenty patients with known polyps underwent CT colonography in the supine position. CT colonographic data were processed by using a shape-based algorithm that depicts masses that protrude into the lumen. We studied nine shape criteria and three isosurface threshold settings. Results were compared with those of conventional colonoscopy performed the same day. RESULTS: There were 50 polyps (28 were ≥10 mm in size; 12, 5-9 mm; 10, <5 mm). The sensitivity with optimal settings for detecting polyps 10 mm or greater was 64% (18 of 28). Sensitivity improved to 71% (10 of 14) for polyps 10 mm or greater in well-distended colonic segments. Performance decreased for polyps less than 10 mm, poorly distended colonic segments, and other shape algorithms. There was a mean of six false-positive lesion sites per colon. These sites were reduced 39% to 3.5 per colon by sampling CT attenuation at the lesion site and discarding sites having attenuation less than a threshold. CONCLUSION: Automated detection of colonic polyps, especially clinically important large polyps, is feasible. Colonic distention is an important determinant of sensitivity. Further increases in sensitivity may be achieved by adding prone CT colonography.

KW - Colon neoplasms, diagnosis, 75.12115, 75.12119, 75.1282, 75.311

KW - Colon, CT, 75.12115, 75.12119, 75.1282

KW - Computed tomography (CT)

KW - Computed tomography (CT), Computer programs

KW - Computed tomography (CT), Image processing

KW - Three-dimensional, 75.12117

UR - http://www.scopus.com/inward/record.url?scp=0035082310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035082310&partnerID=8YFLogxK

U2 - 10.1148/radiology.219.1.r01ap0751

DO - 10.1148/radiology.219.1.r01ap0751

M3 - Article

C2 - 11274534

AN - SCOPUS:0035082310

VL - 219

SP - 51

EP - 59

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 1

ER -