A systematic review of computer-assisted diagnosis in diagnostic cancer imaging

Leila H. Eadie, Paul Taylor, Adam P. Gibson

Research output: Contribution to journalLiterature review

66 Citations (Scopus)

Abstract

Objectives: This study reviews the evidence for the effectiveness of computer-assisted diagnosis (CAD) in cancer imaging. Diagnostic applications were studied to estimate the impact of CAD on radiologists' detection and diagnosis of cancer lesions.

Methods: Online databases were searched and 48 studies from 1992 to 2010 were included: 16 with radiologists using CAD to detect lesions (CADe) and 32 with radiologists using CAD to classify or diagnose lesions (CADx). Weighted means, statistics, summary receiver operating characteristics (SROC) curves, and related measures were used for analysis.

Results: There is evidence that CADx significantly improves diagnosis in mammography and breast ultrasound. In contrast, studies of CADx applied to lung CT and dermatologic imaging show an adverse impact on diagnosis. Overall, there is no evidence of a benefit due to the use of CADe. The area under the SROC curves was not significantly increased for radiologists using either CADe or CADx.

Conclusions: From this analysis it seems CADx can offer some benefit to radiologists in specific imaging applications for breast cancer diagnosis. There is no evidence of a beneficial effect in other applications of CAD and some evidence of a detrimental one. (C) 2011 Elsevier Ireland Ltd. All rights reserved.

Original languageEnglish
Pages (from-to)e70-e76
Number of pages7
JournalEuropean Journal of Radiology
Volume81
Issue number1
DOIs
Publication statusPublished - Jan 2012

Keywords

  • diagnosis
  • computer-assisted image interpretation
  • computer-assisted radiographic image interpretation
  • computer-assisted diagnostic imaging
  • decision making computer-assisted
  • early detection of cancer

Cite this

A systematic review of computer-assisted diagnosis in diagnostic cancer imaging. / Eadie, Leila H.; Taylor, Paul; Gibson, Adam P.

In: European Journal of Radiology, Vol. 81, No. 1, 01.2012, p. e70-e76.

Research output: Contribution to journalLiterature review

Eadie, Leila H. ; Taylor, Paul ; Gibson, Adam P. / A systematic review of computer-assisted diagnosis in diagnostic cancer imaging. In: European Journal of Radiology. 2012 ; Vol. 81, No. 1. pp. e70-e76.
@article{16cee4375cf743c198b44488231c4f18,
title = "A systematic review of computer-assisted diagnosis in diagnostic cancer imaging",
abstract = "Objectives: This study reviews the evidence for the effectiveness of computer-assisted diagnosis (CAD) in cancer imaging. Diagnostic applications were studied to estimate the impact of CAD on radiologists' detection and diagnosis of cancer lesions.Methods: Online databases were searched and 48 studies from 1992 to 2010 were included: 16 with radiologists using CAD to detect lesions (CADe) and 32 with radiologists using CAD to classify or diagnose lesions (CADx). Weighted means, statistics, summary receiver operating characteristics (SROC) curves, and related measures were used for analysis.Results: There is evidence that CADx significantly improves diagnosis in mammography and breast ultrasound. In contrast, studies of CADx applied to lung CT and dermatologic imaging show an adverse impact on diagnosis. Overall, there is no evidence of a benefit due to the use of CADe. The area under the SROC curves was not significantly increased for radiologists using either CADe or CADx.Conclusions: From this analysis it seems CADx can offer some benefit to radiologists in specific imaging applications for breast cancer diagnosis. There is no evidence of a beneficial effect in other applications of CAD and some evidence of a detrimental one. (C) 2011 Elsevier Ireland Ltd. All rights reserved.",
keywords = "diagnosis, computer-assisted image interpretation, computer-assisted radiographic image interpretation, computer-assisted diagnostic imaging, decision making computer-assisted, early detection of cancer",
author = "Eadie, {Leila H.} and Paul Taylor and Gibson, {Adam P.}",
year = "2012",
month = "1",
doi = "10.1016/j.ejrad.2011.01.098",
language = "English",
volume = "81",
pages = "e70--e76",
journal = "European Journal of Radiology",
issn = "0720-048X",
publisher = "Elsevier Ireland Ltd",
number = "1",

}

TY - JOUR

T1 - A systematic review of computer-assisted diagnosis in diagnostic cancer imaging

AU - Eadie, Leila H.

AU - Taylor, Paul

AU - Gibson, Adam P.

PY - 2012/1

Y1 - 2012/1

N2 - Objectives: This study reviews the evidence for the effectiveness of computer-assisted diagnosis (CAD) in cancer imaging. Diagnostic applications were studied to estimate the impact of CAD on radiologists' detection and diagnosis of cancer lesions.Methods: Online databases were searched and 48 studies from 1992 to 2010 were included: 16 with radiologists using CAD to detect lesions (CADe) and 32 with radiologists using CAD to classify or diagnose lesions (CADx). Weighted means, statistics, summary receiver operating characteristics (SROC) curves, and related measures were used for analysis.Results: There is evidence that CADx significantly improves diagnosis in mammography and breast ultrasound. In contrast, studies of CADx applied to lung CT and dermatologic imaging show an adverse impact on diagnosis. Overall, there is no evidence of a benefit due to the use of CADe. The area under the SROC curves was not significantly increased for radiologists using either CADe or CADx.Conclusions: From this analysis it seems CADx can offer some benefit to radiologists in specific imaging applications for breast cancer diagnosis. There is no evidence of a beneficial effect in other applications of CAD and some evidence of a detrimental one. (C) 2011 Elsevier Ireland Ltd. All rights reserved.

AB - Objectives: This study reviews the evidence for the effectiveness of computer-assisted diagnosis (CAD) in cancer imaging. Diagnostic applications were studied to estimate the impact of CAD on radiologists' detection and diagnosis of cancer lesions.Methods: Online databases were searched and 48 studies from 1992 to 2010 were included: 16 with radiologists using CAD to detect lesions (CADe) and 32 with radiologists using CAD to classify or diagnose lesions (CADx). Weighted means, statistics, summary receiver operating characteristics (SROC) curves, and related measures were used for analysis.Results: There is evidence that CADx significantly improves diagnosis in mammography and breast ultrasound. In contrast, studies of CADx applied to lung CT and dermatologic imaging show an adverse impact on diagnosis. Overall, there is no evidence of a benefit due to the use of CADe. The area under the SROC curves was not significantly increased for radiologists using either CADe or CADx.Conclusions: From this analysis it seems CADx can offer some benefit to radiologists in specific imaging applications for breast cancer diagnosis. There is no evidence of a beneficial effect in other applications of CAD and some evidence of a detrimental one. (C) 2011 Elsevier Ireland Ltd. All rights reserved.

KW - diagnosis

KW - computer-assisted image interpretation

KW - computer-assisted radiographic image interpretation

KW - computer-assisted diagnostic imaging

KW - decision making computer-assisted

KW - early detection of cancer

U2 - 10.1016/j.ejrad.2011.01.098

DO - 10.1016/j.ejrad.2011.01.098

M3 - Literature review

VL - 81

SP - e70-e76

JO - European Journal of Radiology

JF - European Journal of Radiology

SN - 0720-048X

IS - 1

ER -