CT colonography

Investigation of the optimum reader paradigm by using computer-aided detection software

Stuart A. Taylor, Susan C. Charman, Philippe Lefere, Elizabeth G. McFarland, Erik K. Paulson, Judy Yee, Rizwan Aslam, John M. Barlow, Arun Gupta, David H. Kim, Chad M. Miller, Steve Halligan

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Purpose: To prospectively compare the diagnostic performance and time efficiency of both second and concurrent computer-aided detection (CAD) reading paradigms for retrospectively obtained computed tomographic (CT) colonography data sets by using consensus reading (three radiologists) of colonoscopic findings as a reference standard. Materials and Methods: Ethical permission, HIPAA compliance (for U.S. institutions), and patient consent were obtained from all institutions for use of CT colonography data sets in this study. Ten radiologists each read 25 CT colonography data sets (12 men, 13 women; mean age, 61 years) containing 69 polyps (28 were 1-5 mm, 41 were ≥6 mm) by using workstations integrated with CAD software. Reading was randomized to either "second read" CAD (applied only after initial unassisted assessment) or "concurrent read" CAD (applied at the start of assessment). Data sets were reread 6 weeks later by using the opposing paradigm. Polyp sensitivity and reading times were compared by using multilevel logistic and linear regression, respectively. Receiver operating characteristic (ROC) curves were generated. Results: Compared with the unassisted read, odds of improved polyp (≥6 mm) detection were 1.5 (95% confidence interval [CI]: 1.0, 2.2) and 1.3 (95% CI: 0.9, 1.9) by using CAD as second and concurrent reader, respectively. Detection odds by using CAD concurrently were 0.87 (95% CI: 0.59, 1.3) and 0.76 (95% CI: 0.57, 1.01) those of second read CAD, excluding and including polyps 1-5 mm, respectively. The concurrent read took 2.9 minutes (95% CI: -3.8, -1.9) less than did second read. The mean areas under the ROC curve (95% CI) for the unassisted read, second read CAD, and concurrent read CAD were 0.83 (95% CI: 0.78, 0.87), 0.86 (95% CI: 0.82, 0.90), and 0.88 (95% CI: 0.83, 0.92), respectively. Conclusion: CAD is more time efficient when used concurrently than when used as a second reader, with similar sensitivity for polyps 6 mm or larger. However, use of second read CAD maximizes sensitivity, particularly for smaller lesions.

Original languageEnglish (US)
Pages (from-to)463-471
Number of pages9
JournalRadiology
Volume246
Issue number2
DOIs
StatePublished - Feb 1 2008
Externally publishedYes

Fingerprint

Computed Tomographic Colonography
Software
Confidence Intervals
Polyps
Reading
ROC Curve
Health Insurance Portability and Accountability Act
Compliance
Linear Models

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Taylor, S. A., Charman, S. C., Lefere, P., McFarland, E. G., Paulson, E. K., Yee, J., ... Halligan, S. (2008). CT colonography: Investigation of the optimum reader paradigm by using computer-aided detection software. Radiology, 246(2), 463-471. https://doi.org/10.1148/radiol.2461070190

CT colonography : Investigation of the optimum reader paradigm by using computer-aided detection software. / Taylor, Stuart A.; Charman, Susan C.; Lefere, Philippe; McFarland, Elizabeth G.; Paulson, Erik K.; Yee, Judy; Aslam, Rizwan; Barlow, John M.; Gupta, Arun; Kim, David H.; Miller, Chad M.; Halligan, Steve.

In: Radiology, Vol. 246, No. 2, 01.02.2008, p. 463-471.

Research output: Contribution to journalArticle

Taylor, SA, Charman, SC, Lefere, P, McFarland, EG, Paulson, EK, Yee, J, Aslam, R, Barlow, JM, Gupta, A, Kim, DH, Miller, CM & Halligan, S 2008, 'CT colonography: Investigation of the optimum reader paradigm by using computer-aided detection software', Radiology, vol. 246, no. 2, pp. 463-471. https://doi.org/10.1148/radiol.2461070190
Taylor, Stuart A. ; Charman, Susan C. ; Lefere, Philippe ; McFarland, Elizabeth G. ; Paulson, Erik K. ; Yee, Judy ; Aslam, Rizwan ; Barlow, John M. ; Gupta, Arun ; Kim, David H. ; Miller, Chad M. ; Halligan, Steve. / CT colonography : Investigation of the optimum reader paradigm by using computer-aided detection software. In: Radiology. 2008 ; Vol. 246, No. 2. pp. 463-471.
@article{1912e73702ff489194e07da008da7dfc,
title = "CT colonography: Investigation of the optimum reader paradigm by using computer-aided detection software",
abstract = "Purpose: To prospectively compare the diagnostic performance and time efficiency of both second and concurrent computer-aided detection (CAD) reading paradigms for retrospectively obtained computed tomographic (CT) colonography data sets by using consensus reading (three radiologists) of colonoscopic findings as a reference standard. Materials and Methods: Ethical permission, HIPAA compliance (for U.S. institutions), and patient consent were obtained from all institutions for use of CT colonography data sets in this study. Ten radiologists each read 25 CT colonography data sets (12 men, 13 women; mean age, 61 years) containing 69 polyps (28 were 1-5 mm, 41 were ≥6 mm) by using workstations integrated with CAD software. Reading was randomized to either {"}second read{"} CAD (applied only after initial unassisted assessment) or {"}concurrent read{"} CAD (applied at the start of assessment). Data sets were reread 6 weeks later by using the opposing paradigm. Polyp sensitivity and reading times were compared by using multilevel logistic and linear regression, respectively. Receiver operating characteristic (ROC) curves were generated. Results: Compared with the unassisted read, odds of improved polyp (≥6 mm) detection were 1.5 (95{\%} confidence interval [CI]: 1.0, 2.2) and 1.3 (95{\%} CI: 0.9, 1.9) by using CAD as second and concurrent reader, respectively. Detection odds by using CAD concurrently were 0.87 (95{\%} CI: 0.59, 1.3) and 0.76 (95{\%} CI: 0.57, 1.01) those of second read CAD, excluding and including polyps 1-5 mm, respectively. The concurrent read took 2.9 minutes (95{\%} CI: -3.8, -1.9) less than did second read. The mean areas under the ROC curve (95{\%} CI) for the unassisted read, second read CAD, and concurrent read CAD were 0.83 (95{\%} CI: 0.78, 0.87), 0.86 (95{\%} CI: 0.82, 0.90), and 0.88 (95{\%} CI: 0.83, 0.92), respectively. Conclusion: CAD is more time efficient when used concurrently than when used as a second reader, with similar sensitivity for polyps 6 mm or larger. However, use of second read CAD maximizes sensitivity, particularly for smaller lesions.",
author = "Taylor, {Stuart A.} and Charman, {Susan C.} and Philippe Lefere and McFarland, {Elizabeth G.} and Paulson, {Erik K.} and Judy Yee and Rizwan Aslam and Barlow, {John M.} and Arun Gupta and Kim, {David H.} and Miller, {Chad M.} and Steve Halligan",
year = "2008",
month = "2",
day = "1",
doi = "10.1148/radiol.2461070190",
language = "English (US)",
volume = "246",
pages = "463--471",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "2",

}

TY - JOUR

T1 - CT colonography

T2 - Investigation of the optimum reader paradigm by using computer-aided detection software

AU - Taylor, Stuart A.

AU - Charman, Susan C.

AU - Lefere, Philippe

AU - McFarland, Elizabeth G.

AU - Paulson, Erik K.

AU - Yee, Judy

AU - Aslam, Rizwan

AU - Barlow, John M.

AU - Gupta, Arun

AU - Kim, David H.

AU - Miller, Chad M.

AU - Halligan, Steve

PY - 2008/2/1

Y1 - 2008/2/1

N2 - Purpose: To prospectively compare the diagnostic performance and time efficiency of both second and concurrent computer-aided detection (CAD) reading paradigms for retrospectively obtained computed tomographic (CT) colonography data sets by using consensus reading (three radiologists) of colonoscopic findings as a reference standard. Materials and Methods: Ethical permission, HIPAA compliance (for U.S. institutions), and patient consent were obtained from all institutions for use of CT colonography data sets in this study. Ten radiologists each read 25 CT colonography data sets (12 men, 13 women; mean age, 61 years) containing 69 polyps (28 were 1-5 mm, 41 were ≥6 mm) by using workstations integrated with CAD software. Reading was randomized to either "second read" CAD (applied only after initial unassisted assessment) or "concurrent read" CAD (applied at the start of assessment). Data sets were reread 6 weeks later by using the opposing paradigm. Polyp sensitivity and reading times were compared by using multilevel logistic and linear regression, respectively. Receiver operating characteristic (ROC) curves were generated. Results: Compared with the unassisted read, odds of improved polyp (≥6 mm) detection were 1.5 (95% confidence interval [CI]: 1.0, 2.2) and 1.3 (95% CI: 0.9, 1.9) by using CAD as second and concurrent reader, respectively. Detection odds by using CAD concurrently were 0.87 (95% CI: 0.59, 1.3) and 0.76 (95% CI: 0.57, 1.01) those of second read CAD, excluding and including polyps 1-5 mm, respectively. The concurrent read took 2.9 minutes (95% CI: -3.8, -1.9) less than did second read. The mean areas under the ROC curve (95% CI) for the unassisted read, second read CAD, and concurrent read CAD were 0.83 (95% CI: 0.78, 0.87), 0.86 (95% CI: 0.82, 0.90), and 0.88 (95% CI: 0.83, 0.92), respectively. Conclusion: CAD is more time efficient when used concurrently than when used as a second reader, with similar sensitivity for polyps 6 mm or larger. However, use of second read CAD maximizes sensitivity, particularly for smaller lesions.

AB - Purpose: To prospectively compare the diagnostic performance and time efficiency of both second and concurrent computer-aided detection (CAD) reading paradigms for retrospectively obtained computed tomographic (CT) colonography data sets by using consensus reading (three radiologists) of colonoscopic findings as a reference standard. Materials and Methods: Ethical permission, HIPAA compliance (for U.S. institutions), and patient consent were obtained from all institutions for use of CT colonography data sets in this study. Ten radiologists each read 25 CT colonography data sets (12 men, 13 women; mean age, 61 years) containing 69 polyps (28 were 1-5 mm, 41 were ≥6 mm) by using workstations integrated with CAD software. Reading was randomized to either "second read" CAD (applied only after initial unassisted assessment) or "concurrent read" CAD (applied at the start of assessment). Data sets were reread 6 weeks later by using the opposing paradigm. Polyp sensitivity and reading times were compared by using multilevel logistic and linear regression, respectively. Receiver operating characteristic (ROC) curves were generated. Results: Compared with the unassisted read, odds of improved polyp (≥6 mm) detection were 1.5 (95% confidence interval [CI]: 1.0, 2.2) and 1.3 (95% CI: 0.9, 1.9) by using CAD as second and concurrent reader, respectively. Detection odds by using CAD concurrently were 0.87 (95% CI: 0.59, 1.3) and 0.76 (95% CI: 0.57, 1.01) those of second read CAD, excluding and including polyps 1-5 mm, respectively. The concurrent read took 2.9 minutes (95% CI: -3.8, -1.9) less than did second read. The mean areas under the ROC curve (95% CI) for the unassisted read, second read CAD, and concurrent read CAD were 0.83 (95% CI: 0.78, 0.87), 0.86 (95% CI: 0.82, 0.90), and 0.88 (95% CI: 0.83, 0.92), respectively. Conclusion: CAD is more time efficient when used concurrently than when used as a second reader, with similar sensitivity for polyps 6 mm or larger. However, use of second read CAD maximizes sensitivity, particularly for smaller lesions.

UR - http://www.scopus.com/inward/record.url?scp=39549098130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39549098130&partnerID=8YFLogxK

U2 - 10.1148/radiol.2461070190

DO - 10.1148/radiol.2461070190

M3 - Article

VL - 246

SP - 463

EP - 471

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 2

ER -