2006
DOI: 10.2214/ajr.04.1990
|View full text |Cite
|
Sign up to set email alerts
|

Computer-Assisted Reader Software Versus Expert Reviewers for Polyp Detection on CT Colonography

Abstract: ColonCAR version 1.2 is sensitive for polyp detection, with a clinically acceptable false-positive rate. ColonCAR version 1.2 has a synergistic effect to the reviewer alone, and its standalone performance may exceed even that of experts.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
32
0

Year Published

2008
2008
2015
2015

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 68 publications
(34 citation statements)
references
References 23 publications
2
32
0
Order By: Relevance
“…In stand-alone studies ( 4-6 ), CAD has been shown to be sensitive for detection of polyps, but reader studies are critical to demonstrate the practical value of CAD because readers may accept or reject CAD marks, and there is a potential for sensitivity and specifi city to improve or deteriorate. Multireader CAD trials, to date, have generally included either small patient cohorts or small numbers of readers, often addressing a specifi c narrow question ( 4,6,8,(12)(13)(14)(15)(16)(17)(18)(19)(20) such as cost-effectiveness of CAD ( 21 ). Two trials have included lowprevalence cohorts ( 22 ) or large cohorts ( 10 ).…”
Section: Methodsmentioning
confidence: 99%
“…In stand-alone studies ( 4-6 ), CAD has been shown to be sensitive for detection of polyps, but reader studies are critical to demonstrate the practical value of CAD because readers may accept or reject CAD marks, and there is a potential for sensitivity and specifi city to improve or deteriorate. Multireader CAD trials, to date, have generally included either small patient cohorts or small numbers of readers, often addressing a specifi c narrow question ( 4,6,8,(12)(13)(14)(15)(16)(17)(18)(19)(20) such as cost-effectiveness of CAD ( 21 ). Two trials have included lowprevalence cohorts ( 22 ) or large cohorts ( 10 ).…”
Section: Methodsmentioning
confidence: 99%
“…The "stand-alone" performance of a CAD algorithm excludes the radiologist interaction, and merely reports the ability of the software to detect true polyps (sensitivity) and reports the number of false-positive detections per series, which is equivalent to 1-specificity. Since 2002, several researchers have reported the stand-alone sensitivity and specificity of various academic and commercial CAD systems [4,5]. As CAD schemes evolve, performances improve in tandem.…”
Section: Inside the Black Boxmentioning
confidence: 99%
“…In most studies, the sensitivity of CAD in isolation has been superior to that achieved by radiologists assisted by the same CAD algorithm [5]. It is clear that diminished sensitivity is due to the fact that readers ignore a percentage of true-positive CAD marks [11,20].…”
Section: Limits Of Knowledge Of Cad Performance and Controversiesmentioning
confidence: 99%
“…Computer-aided detection (CAD) is a promising technique [2][3][4][5] that could be helpful in reducing these falsenegative findings [6,7]. However, even if the CAD performance would be excellent, it does not automatically translate into equivalent reader performance [8,9], i.e., CAD hits can be disregarded by the observer.…”
Section: Introductionmentioning
confidence: 99%