Computed Tomography Colonography: Feasibility of Computer-Aided Polyp Detection in a "First Reader" Paradigm

Aravind Mani, Sandy Napel, David S. Paik, R. Brooke Jeffrey, Judy Yee, Eric W. Olcott, Rupert Prokesch, Marta Davila, Pamela Schraedley-Desmond, Christopher F. Beaulieu

Research output: Contribution to journalArticle

57 Citations (Scopus)

Abstract

Objective: To determine the feasibility of a computer-aided detection (CAD) algorithm as the "first reader" in computed tomography colonography (CTC). Methods: In phase 1 of a 2-part blind trial, we measured the performance of 3 radiologists reading 41 CTC studies without CAD. In phase 2, readers interpreted the same cases using a CAD list of 30 potential polyps. Results: Unassisted readers detected, on average, 63% of polyps ≥ 10 mm in diameter. Using CAD, the sensitivity was 74% (not statistically different). Per-patient analysis showed a trend toward increased sensitivity for polyps ≥10 mm in diameter, from 73% to 90% with CAD (not significant) without decreasing specificity. Computer-aided detection significantly decreased interobserver variability (P = 0.017). Average time to detection of the first polyp decreased significantly with CAD, whereas total reading case reading time was unchanged. Conclusion: Computer-aided detection as a first reader in CTC was associated with similar per-polyp and per-patient detection sensitivity to unassisted reading. Computer-aided detection decreased interobserver variability and reduced the time required to detect the first polyp.

Original languageEnglish (US)
Pages (from-to)318-326
Number of pages9
JournalJournal of Computer Assisted Tomography
Volume28
Issue number3
DOIs
StatePublished - May 1 2004
Externally publishedYes

Fingerprint

Polyps
Tomography
Reading
Observer Variation

Keywords

  • Colon
  • Computed tomography colonography
  • Computer-aided diagnosis
  • Interpretation accuracy
  • Interpretation efficiency
  • Polyps
  • Virtual colonoscopy

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Computed Tomography Colonography : Feasibility of Computer-Aided Polyp Detection in a "First Reader" Paradigm. / Mani, Aravind; Napel, Sandy; Paik, David S.; Jeffrey, R. Brooke; Yee, Judy; Olcott, Eric W.; Prokesch, Rupert; Davila, Marta; Schraedley-Desmond, Pamela; Beaulieu, Christopher F.

In: Journal of Computer Assisted Tomography, Vol. 28, No. 3, 01.05.2004, p. 318-326.

Research output: Contribution to journalArticle

Mani, A, Napel, S, Paik, DS, Jeffrey, RB, Yee, J, Olcott, EW, Prokesch, R, Davila, M, Schraedley-Desmond, P & Beaulieu, CF 2004, 'Computed Tomography Colonography: Feasibility of Computer-Aided Polyp Detection in a "First Reader" Paradigm', Journal of Computer Assisted Tomography, vol. 28, no. 3, pp. 318-326. https://doi.org/10.1097/00004728-200405000-00003
Mani, Aravind ; Napel, Sandy ; Paik, David S. ; Jeffrey, R. Brooke ; Yee, Judy ; Olcott, Eric W. ; Prokesch, Rupert ; Davila, Marta ; Schraedley-Desmond, Pamela ; Beaulieu, Christopher F. / Computed Tomography Colonography : Feasibility of Computer-Aided Polyp Detection in a "First Reader" Paradigm. In: Journal of Computer Assisted Tomography. 2004 ; Vol. 28, No. 3. pp. 318-326.
@article{524a6094b6c2476e93fe9131359042a0,
title = "Computed Tomography Colonography: Feasibility of Computer-Aided Polyp Detection in a {"}First Reader{"} Paradigm",
abstract = "Objective: To determine the feasibility of a computer-aided detection (CAD) algorithm as the {"}first reader{"} in computed tomography colonography (CTC). Methods: In phase 1 of a 2-part blind trial, we measured the performance of 3 radiologists reading 41 CTC studies without CAD. In phase 2, readers interpreted the same cases using a CAD list of 30 potential polyps. Results: Unassisted readers detected, on average, 63{\%} of polyps ≥ 10 mm in diameter. Using CAD, the sensitivity was 74{\%} (not statistically different). Per-patient analysis showed a trend toward increased sensitivity for polyps ≥10 mm in diameter, from 73{\%} to 90{\%} with CAD (not significant) without decreasing specificity. Computer-aided detection significantly decreased interobserver variability (P = 0.017). Average time to detection of the first polyp decreased significantly with CAD, whereas total reading case reading time was unchanged. Conclusion: Computer-aided detection as a first reader in CTC was associated with similar per-polyp and per-patient detection sensitivity to unassisted reading. Computer-aided detection decreased interobserver variability and reduced the time required to detect the first polyp.",
keywords = "Colon, Computed tomography colonography, Computer-aided diagnosis, Interpretation accuracy, Interpretation efficiency, Polyps, Virtual colonoscopy",
author = "Aravind Mani and Sandy Napel and Paik, {David S.} and Jeffrey, {R. Brooke} and Judy Yee and Olcott, {Eric W.} and Rupert Prokesch and Marta Davila and Pamela Schraedley-Desmond and Beaulieu, {Christopher F.}",
year = "2004",
month = "5",
day = "1",
doi = "10.1097/00004728-200405000-00003",
language = "English (US)",
volume = "28",
pages = "318--326",
journal = "Journal of Computer Assisted Tomography",
issn = "0363-8715",
publisher = "Lippincott Williams and Wilkins",
number = "3",

}

TY - JOUR

T1 - Computed Tomography Colonography

T2 - Feasibility of Computer-Aided Polyp Detection in a "First Reader" Paradigm

AU - Mani, Aravind

AU - Napel, Sandy

AU - Paik, David S.

AU - Jeffrey, R. Brooke

AU - Yee, Judy

AU - Olcott, Eric W.

AU - Prokesch, Rupert

AU - Davila, Marta

AU - Schraedley-Desmond, Pamela

AU - Beaulieu, Christopher F.

PY - 2004/5/1

Y1 - 2004/5/1

N2 - Objective: To determine the feasibility of a computer-aided detection (CAD) algorithm as the "first reader" in computed tomography colonography (CTC). Methods: In phase 1 of a 2-part blind trial, we measured the performance of 3 radiologists reading 41 CTC studies without CAD. In phase 2, readers interpreted the same cases using a CAD list of 30 potential polyps. Results: Unassisted readers detected, on average, 63% of polyps ≥ 10 mm in diameter. Using CAD, the sensitivity was 74% (not statistically different). Per-patient analysis showed a trend toward increased sensitivity for polyps ≥10 mm in diameter, from 73% to 90% with CAD (not significant) without decreasing specificity. Computer-aided detection significantly decreased interobserver variability (P = 0.017). Average time to detection of the first polyp decreased significantly with CAD, whereas total reading case reading time was unchanged. Conclusion: Computer-aided detection as a first reader in CTC was associated with similar per-polyp and per-patient detection sensitivity to unassisted reading. Computer-aided detection decreased interobserver variability and reduced the time required to detect the first polyp.

AB - Objective: To determine the feasibility of a computer-aided detection (CAD) algorithm as the "first reader" in computed tomography colonography (CTC). Methods: In phase 1 of a 2-part blind trial, we measured the performance of 3 radiologists reading 41 CTC studies without CAD. In phase 2, readers interpreted the same cases using a CAD list of 30 potential polyps. Results: Unassisted readers detected, on average, 63% of polyps ≥ 10 mm in diameter. Using CAD, the sensitivity was 74% (not statistically different). Per-patient analysis showed a trend toward increased sensitivity for polyps ≥10 mm in diameter, from 73% to 90% with CAD (not significant) without decreasing specificity. Computer-aided detection significantly decreased interobserver variability (P = 0.017). Average time to detection of the first polyp decreased significantly with CAD, whereas total reading case reading time was unchanged. Conclusion: Computer-aided detection as a first reader in CTC was associated with similar per-polyp and per-patient detection sensitivity to unassisted reading. Computer-aided detection decreased interobserver variability and reduced the time required to detect the first polyp.

KW - Colon

KW - Computed tomography colonography

KW - Computer-aided diagnosis

KW - Interpretation accuracy

KW - Interpretation efficiency

KW - Polyps

KW - Virtual colonoscopy

UR - http://www.scopus.com/inward/record.url?scp=2342549663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2342549663&partnerID=8YFLogxK

U2 - 10.1097/00004728-200405000-00003

DO - 10.1097/00004728-200405000-00003

M3 - Article

C2 - 15100534

AN - SCOPUS:2342549663

VL - 28

SP - 318

EP - 326

JO - Journal of Computer Assisted Tomography

JF - Journal of Computer Assisted Tomography

SN - 0363-8715

IS - 3

ER -