Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging

A stand-alone evaluation

Thomas Mang, Luca Bogoni, Marcos Salganicoff, Matthias Wolf, Vikas Raykar, Michael MacAri, Perry J. Pickhardt, Franco Iafrate, Andrea Laghi, Michael Weber, Mark E. Baker, Helmut Ringl, Christian J. Herold, Anno Graser

Research output: Contribution to journalArticle

Abstract

Purpose: To evaluate the stand-alone performance of a computer-aided detection (CAD) algorithm for colorectal polyps in a large heterogeneous CT colonography (CTC) database that included both tagged and untagged datasets. Methods: Written, informed consent was waived for this institutional review board-approved, HIPAA-compliant retrospective study. CTC datasets from 2063 patients were assigned to training (n = 374) and testing (n = 1689). The test set consisted of 836 untagged and 853 tagged examinations not used for CAD training. Examinations were performed at 15 sites in the United States, Asia, and Europe, using 4-to 64-multidetector-row computed tomography and various acquisition parameters. CAD sensitivities were calculated on a per-patient and per-polyp basis for polyps measuring ≥6 mm. The reference standard was colonoscopy in 1588 (94%) and consensus interpretation by expert radiologists in 101 (6%) patients. Statistical testing employed χ 2, logistic regression, and Mann-Whitney U tests. Results: In 383 of 1689 individuals, 564 polyps measuring ≥6 mm were identified by the reference standard (347 polyps: 6-9 mm and 217 polyps: ≥10 mm). Overall, CAD per-patient sensitivity was 89.6% (343/383), with 89.0% (187/210) for untagged and 90.2% (156/173) for tagged datasets (P = 0.72). Overall, per-polyp sensitivity was 86.9% (490/564), with 84.4% (270/320) for untagged and 90.2% (220/244) for tagged examinations (P = 068). The mean false-positive rate per patient was 5.14 (median, 4) in untagged and 4.67 (median, 4) in tagged patient datasets (P = 0.353). Conclusion: Stand-alone CAD can be applied to both tagged and untagged CTC studies without significant performance differences. Detection rates are comparable to human readers at a relatively low false-positive rate, making CAD a useful tool in clinical practice.

Original languageEnglish (US)
Pages (from-to)99-108
Number of pages10
JournalInvestigative Radiology
Volume47
Issue number2
DOIs
StatePublished - Feb 2012
Externally publishedYes

Fingerprint

Computed Tomographic Colonography
Polyps
Health Insurance Portability and Accountability Act
Multidetector Computed Tomography
Research Ethics Committees
Colonoscopy
Nonparametric Statistics
Informed Consent
Retrospective Studies
Logistic Models
Databases
Datasets

Keywords

  • colorectal cancer
  • colorectal polyps
  • computer-aided detection
  • CT colonography
  • virtual colonoscopy

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging : A stand-alone evaluation. / Mang, Thomas; Bogoni, Luca; Salganicoff, Marcos; Wolf, Matthias; Raykar, Vikas; MacAri, Michael; Pickhardt, Perry J.; Iafrate, Franco; Laghi, Andrea; Weber, Michael; Baker, Mark E.; Ringl, Helmut; Herold, Christian J.; Graser, Anno.

In: Investigative Radiology, Vol. 47, No. 2, 02.2012, p. 99-108.

Research output: Contribution to journalArticle

Mang, T, Bogoni, L, Salganicoff, M, Wolf, M, Raykar, V, MacAri, M, Pickhardt, PJ, Iafrate, F, Laghi, A, Weber, M, Baker, ME, Ringl, H, Herold, CJ & Graser, A 2012, 'Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging: A stand-alone evaluation', Investigative Radiology, vol. 47, no. 2, pp. 99-108. https://doi.org/10.1097/RLI.0b013e31822b41e1
Mang, Thomas ; Bogoni, Luca ; Salganicoff, Marcos ; Wolf, Matthias ; Raykar, Vikas ; MacAri, Michael ; Pickhardt, Perry J. ; Iafrate, Franco ; Laghi, Andrea ; Weber, Michael ; Baker, Mark E. ; Ringl, Helmut ; Herold, Christian J. ; Graser, Anno. / Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging : A stand-alone evaluation. In: Investigative Radiology. 2012 ; Vol. 47, No. 2. pp. 99-108.
@article{b20bb26bf7f9413c85182463df0ac39c,
title = "Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging: A stand-alone evaluation",
abstract = "Purpose: To evaluate the stand-alone performance of a computer-aided detection (CAD) algorithm for colorectal polyps in a large heterogeneous CT colonography (CTC) database that included both tagged and untagged datasets. Methods: Written, informed consent was waived for this institutional review board-approved, HIPAA-compliant retrospective study. CTC datasets from 2063 patients were assigned to training (n = 374) and testing (n = 1689). The test set consisted of 836 untagged and 853 tagged examinations not used for CAD training. Examinations were performed at 15 sites in the United States, Asia, and Europe, using 4-to 64-multidetector-row computed tomography and various acquisition parameters. CAD sensitivities were calculated on a per-patient and per-polyp basis for polyps measuring ≥6 mm. The reference standard was colonoscopy in 1588 (94{\%}) and consensus interpretation by expert radiologists in 101 (6{\%}) patients. Statistical testing employed χ 2, logistic regression, and Mann-Whitney U tests. Results: In 383 of 1689 individuals, 564 polyps measuring ≥6 mm were identified by the reference standard (347 polyps: 6-9 mm and 217 polyps: ≥10 mm). Overall, CAD per-patient sensitivity was 89.6{\%} (343/383), with 89.0{\%} (187/210) for untagged and 90.2{\%} (156/173) for tagged datasets (P = 0.72). Overall, per-polyp sensitivity was 86.9{\%} (490/564), with 84.4{\%} (270/320) for untagged and 90.2{\%} (220/244) for tagged examinations (P = 068). The mean false-positive rate per patient was 5.14 (median, 4) in untagged and 4.67 (median, 4) in tagged patient datasets (P = 0.353). Conclusion: Stand-alone CAD can be applied to both tagged and untagged CTC studies without significant performance differences. Detection rates are comparable to human readers at a relatively low false-positive rate, making CAD a useful tool in clinical practice.",
keywords = "colorectal cancer, colorectal polyps, computer-aided detection, CT colonography, virtual colonoscopy",
author = "Thomas Mang and Luca Bogoni and Marcos Salganicoff and Matthias Wolf and Vikas Raykar and Michael MacAri and Pickhardt, {Perry J.} and Franco Iafrate and Andrea Laghi and Michael Weber and Baker, {Mark E.} and Helmut Ringl and Herold, {Christian J.} and Anno Graser",
year = "2012",
month = "2",
doi = "10.1097/RLI.0b013e31822b41e1",
language = "English (US)",
volume = "47",
pages = "99--108",
journal = "Investigative Radiology",
issn = "0020-9996",
publisher = "Lippincott Williams and Wilkins",
number = "2",

}

TY - JOUR

T1 - Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging

T2 - A stand-alone evaluation

AU - Mang, Thomas

AU - Bogoni, Luca

AU - Salganicoff, Marcos

AU - Wolf, Matthias

AU - Raykar, Vikas

AU - MacAri, Michael

AU - Pickhardt, Perry J.

AU - Iafrate, Franco

AU - Laghi, Andrea

AU - Weber, Michael

AU - Baker, Mark E.

AU - Ringl, Helmut

AU - Herold, Christian J.

AU - Graser, Anno

PY - 2012/2

Y1 - 2012/2

N2 - Purpose: To evaluate the stand-alone performance of a computer-aided detection (CAD) algorithm for colorectal polyps in a large heterogeneous CT colonography (CTC) database that included both tagged and untagged datasets. Methods: Written, informed consent was waived for this institutional review board-approved, HIPAA-compliant retrospective study. CTC datasets from 2063 patients were assigned to training (n = 374) and testing (n = 1689). The test set consisted of 836 untagged and 853 tagged examinations not used for CAD training. Examinations were performed at 15 sites in the United States, Asia, and Europe, using 4-to 64-multidetector-row computed tomography and various acquisition parameters. CAD sensitivities were calculated on a per-patient and per-polyp basis for polyps measuring ≥6 mm. The reference standard was colonoscopy in 1588 (94%) and consensus interpretation by expert radiologists in 101 (6%) patients. Statistical testing employed χ 2, logistic regression, and Mann-Whitney U tests. Results: In 383 of 1689 individuals, 564 polyps measuring ≥6 mm were identified by the reference standard (347 polyps: 6-9 mm and 217 polyps: ≥10 mm). Overall, CAD per-patient sensitivity was 89.6% (343/383), with 89.0% (187/210) for untagged and 90.2% (156/173) for tagged datasets (P = 0.72). Overall, per-polyp sensitivity was 86.9% (490/564), with 84.4% (270/320) for untagged and 90.2% (220/244) for tagged examinations (P = 068). The mean false-positive rate per patient was 5.14 (median, 4) in untagged and 4.67 (median, 4) in tagged patient datasets (P = 0.353). Conclusion: Stand-alone CAD can be applied to both tagged and untagged CTC studies without significant performance differences. Detection rates are comparable to human readers at a relatively low false-positive rate, making CAD a useful tool in clinical practice.

AB - Purpose: To evaluate the stand-alone performance of a computer-aided detection (CAD) algorithm for colorectal polyps in a large heterogeneous CT colonography (CTC) database that included both tagged and untagged datasets. Methods: Written, informed consent was waived for this institutional review board-approved, HIPAA-compliant retrospective study. CTC datasets from 2063 patients were assigned to training (n = 374) and testing (n = 1689). The test set consisted of 836 untagged and 853 tagged examinations not used for CAD training. Examinations were performed at 15 sites in the United States, Asia, and Europe, using 4-to 64-multidetector-row computed tomography and various acquisition parameters. CAD sensitivities were calculated on a per-patient and per-polyp basis for polyps measuring ≥6 mm. The reference standard was colonoscopy in 1588 (94%) and consensus interpretation by expert radiologists in 101 (6%) patients. Statistical testing employed χ 2, logistic regression, and Mann-Whitney U tests. Results: In 383 of 1689 individuals, 564 polyps measuring ≥6 mm were identified by the reference standard (347 polyps: 6-9 mm and 217 polyps: ≥10 mm). Overall, CAD per-patient sensitivity was 89.6% (343/383), with 89.0% (187/210) for untagged and 90.2% (156/173) for tagged datasets (P = 0.72). Overall, per-polyp sensitivity was 86.9% (490/564), with 84.4% (270/320) for untagged and 90.2% (220/244) for tagged examinations (P = 068). The mean false-positive rate per patient was 5.14 (median, 4) in untagged and 4.67 (median, 4) in tagged patient datasets (P = 0.353). Conclusion: Stand-alone CAD can be applied to both tagged and untagged CTC studies without significant performance differences. Detection rates are comparable to human readers at a relatively low false-positive rate, making CAD a useful tool in clinical practice.

KW - colorectal cancer

KW - colorectal polyps

KW - computer-aided detection

KW - CT colonography

KW - virtual colonoscopy

UR - http://www.scopus.com/inward/record.url?scp=84855843787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855843787&partnerID=8YFLogxK

U2 - 10.1097/RLI.0b013e31822b41e1

DO - 10.1097/RLI.0b013e31822b41e1

M3 - Article

VL - 47

SP - 99

EP - 108

JO - Investigative Radiology

JF - Investigative Radiology

SN - 0020-9996

IS - 2

ER -