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

Taylor, Stuart A.; Halligan, Steve; Burling, David; Roddie, Mary E.; Honeyfield, Lesley; McQuillan, Justine; Amin, Hamdan; Dehmeshki, Jamshid

doi:10.2214/ajr.04.1990

Cited by 68 publications

(34 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

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%

Effect of Computer-aided Detection for CT Colonography in a Multireader, Multicase Trial

Dachman¹,

Obuchowski²,

Hoffmeister³

et al. 2010

Radiology

View full text Add to dashboard Cite

Purpose:To assess the effect of using computer-aided detection (CAD) in second-read mode on readers' accuracy in interpreting computed tomographic (CT) colonographic images. Materials and Methods:The contributing institutions performed the examinations under approval of their local institutional review board, with waiver of informed consent, for this HIPAA-compliant study. A cohort of 100 colonoscopy-proved cases was used: In 52 patients with fi ndings positive for polyps, 74 polyps of 6 mm or larger were observed in 65 colonic segments; in 48 patients with fi ndings negative for polyps, no polyps were found. Nineteen blinded readers interpreted each case at two different times, with and without the assistance of a commercial CAD system. The effect of CAD was assessed in segment-level and patient-level receiver operating characteristic (ROC) curve analyses. Results:Thirteen (68%) of 19 readers demonstrated higher accuracy with CAD, as measured with the segment-level area under the ROC curve (AUC). The readers' average segment-level AUC with CAD (0.758) was signifi cantly greater ( P = .015) than the average AUC in the unassisted read (0.737). Readers' per-segment, per-patient, and per-polyp sensitivity for all polyps of 6 mm or larger was higher ( P , .011, .007, .005, respectively) for readings with CAD compared with unassisted readings (0.517 versus 0.465, 0.521 versus 0.466, and 0.477 versus 0.422, respectively). Sensitivity for patients with at least one large polyp of 10 mm or larger was also higher ( P , .047) with CAD than without (0.777 versus 0.743). Average reader sensitivity also improved with CAD by more than 0.08 for small adenomas. Use of CAD reduced specifi city of readers by 0.025 ( P = .05). Conclusion:Use of CAD resulted in a signifi cant improvement in overall reader performance. CAD improves reader sensitivity when measured per segment, per patient, and per polyp for small polyps and adenomas and also reduces specifi city by a small amount.q RSNA, 2010 Supplemental material: http://radiology.rsna.org/lookup /suppl

show abstract

Section: Methodsmentioning

confidence: 99%

Effect of Computer-aided Detection for CT Colonography in a Multireader, Multicase Trial

Dachman¹,

Obuchowski²,

Hoffmeister³

et al. 2010

Radiology

View full text Add to dashboard Cite

show abstract

“…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%

CAD: How it works, how to use it, performance

Regge

Halligan

2013

European Journal of Radiology

Self Cite

View full text Add to dashboard Cite

a b s t r a c tComputer-aided diagnosis (CAD) systems are software algorithms designed to assist radiologists (or other practitioners) in solving a diagnostic problem by using a visual prompt (or "CAD mark") to direct the observer towards potential pathology. CT colonography is a recent arrival to CAD, but could represent one of its most fruitful applications in the future. In contrast to other organs, where a variety of different pathologies are equally represented, significant colorectal pathologies other than polyps and cancer are relatively uncommon. As we shall see, this simplifies the diagnostic task for artificial intelligence developers and also for radiologists who, ultimately, must make the final decision.This review aims to present the current state-of-the-art for CAD applied to CT colonography. A brief overview of the technical essentials and of the diagnostic performance of CAD in isolation, is followed by an explanation of how CAD is used in day-to-day practice. The last section will deal with the most controversial issues affecting CAD performance in clinical practice, with a focus on the interaction between human and artificial intelligence.

show abstract

“…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%

Does a computer-aided detection algorithm in a second read paradigm enhance the performance of experienced computed tomography colonography readers in a population of increased risk?

et al. 2008

View full text Add to dashboard Cite

Does a computer-aided detection algorithm in a second read paradigm enhance the performance of experienced computed tomography colonography readers in a population of increased risk?Abstract We prospectively determined whether computer-aided detection (CAD) could improve the performance characteristics of computed tomography colonography (CTC) in a population of increased risk for colorectal cancer. Therefore, we included 170 consecutive patients that underwent both CTC and colonoscopy. All findings ≥6 mm were evaluated at colonoscopy by segmental unblinding. We determined perpatient sensitivity and specificity for polyps ≥6 mm and ≥10 mm without and with computer-aided detection (CAD). The McNemar test was used for comparison the results without and with CAD. Unblinded colonoscopy detected 50 patients with lesions ≥6 mm and 25 patients with lesions ≥10 mm. Sensitivity of CTC without CAD for these size categories was 80% (40/50, 95% CI: 69-81%) and 64% (16/25, 95% CI: 45-83%), respectively. CTC with CAD detected one additional patient with a lesion ≥6 mm and two with a lesion ≥10 mm, resulting in a sensitivity of 82% (41/50, 95% CI: 71-93%) (p=0.50) and 72% (18/25, 95% CI: 54-90%) (p=1.0), respectively. Specificity without CAD for polyps ≥6 mm and ≥10 mm was 84% (101/120, 95% CI: 78-91%) and 94% (136/145, 95% CI: 90-98%), respectively. With CAD, the specificity remained (nearly) unchanged: 83% (99/120, 95% CI: 76-89%) and 94% (136/145, 95% CI: 90-98%), respectively. Thus, although CTC with CAD detected a few more patients than CTC without CAD, it had no statistically significant positive influence on CTC performance.

show abstract

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.

Cited by 68 publications

References 23 publications

Effect of Computer-aided Detection for CT Colonography in a Multireader, Multicase Trial

Effect of Computer-aided Detection for CT Colonography in a Multireader, Multicase Trial

CAD: How it works, how to use it, performance

Does a computer-aided detection algorithm in a second read paradigm enhance the performance of experienced computed tomography colonography readers in a population of increased risk?

Contact Info

Product

Resources

About