Computer-aided Detection of Colorectal Polyps: Can It Improve Sensitivity of Less-Experienced Readers? Preliminary Findings

Baker, Mark E.; Bogoni, Luca; Obuchowski, Nancy A.; Dass, C.; Kendzierski, Renee M.; Remer, Erick M.; Einstein, David M.; Cathier, Pascal; Jerebko, Anna K.; Lakare, Sarang; Blum, A.; Caroline, Dina F.; Macari, Michael

doi:10.1148/radiol.2451061116

Cited by 74 publications

(57 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, Halligan et al [13] demonstrated that second-read CAD also benefits the experienced CTC reader, finding that mean per-polyp sensitivity for polyps 6 mm or larger increased on average by 9%. As expected, additional interpretation of CAD candidates extends overall CTC reading time by a few minutes [12,14]. 3) "Concurrent" CAD.…”

Section: How To Use Cadmentioning

confidence: 69%

“…Intuitively, second-read CAD should be most beneficial when adopted by less experienced readers; radiologists relatively unfamiliar with CTC have lower detection rates and their gain when using CAD should be larger than for experienced readers [11]. Baker et al [12] have shown that, for polyps 6 mm or larger, second-read CAD improves detection of readers with some or no experience in CTC reporting from 81% to 91%. These authors also found that CAD second-read increases detection of intermediate size polyps.…”

Section: How To Use Cadmentioning

confidence: 99%

See 1 more Smart Citation

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

Regge

Halligan

2013

European Journal of Radiology

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

Section: How To Use Cadmentioning

confidence: 69%

Section: How To Use Cadmentioning

confidence: 99%

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

Regge

Halligan

2013

European Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…Several CTC studies in which the additional value of CAD was evaluated (after the interaction with the observer) have reported good results in terms of polyp detection [12,[25][26][27]. All concluded that the observers detected statistically more polyps with CAD.…”

Section: Discussionmentioning

confidence: 99%

“…Recent studies concluded that in a selected population CAD significantly improved per-polyp sensitivity for less experienced observers [10][11][12][13]. Though experienced observers benefited proportionally less from CAD [14,15].…”

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

“…Computed tomographic colonography (CTC) or virtual colonoscopy has been widely used for detecting colorectal neoplasms via 3D computed tomography (CT) abdomen scans of the cleansed and air-distended colon. In the last decade, many computer aided detection and diagnosis systems [4,5,6,7] have been proposed and actively studied to improve the performance and reliability of human radiologists as second readers.…”

Section: Introductionmentioning

confidence: 99%

A Two-Level Approach Towards Semantic Colon Segmentation: Removing Extra-Colonic Findings

Lü

Wolf

Liang

et al. 2009

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2009

View full text Add to dashboard Cite

Abstract.Computer aided detection (CAD) of colonic polyps in computed tomographic colonography has tremendously impacted colorectal cancer diagnosis using 3D medical imaging. It is a prerequisite for all CAD systems to extract the air-distended colon segments from 3D abdomen computed tomography scans. In this paper, we present a two-level statistical approach of first separating colon segments from small intestine, stomach and other extra-colonic parts by classification on a new geometric feature set; then evaluating the overall performance confidence using distance and geometry statistics over patients. The proposed method is fully automatic and validated using both the classification results in the first level and its numerical impacts on false positive reduction of extra-colonic findings in a CAD system. It shows superior performance than the state-of-art knowledge or anatomy based colon segmentation algorithms [1,2,3].

show abstract

Computer-aided Detection of Colorectal Polyps: Can It Improve Sensitivity of Less-Experienced Readers? Preliminary Findings

Abstract: Results of this feasibility study suggest that CAD for CT colonography significantly improves per-polyp detection for less-experienced readers.

Cited by 74 publications

References 45 publications

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

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?

A Two-Level Approach Towards Semantic Colon Segmentation: Removing Extra-Colonic Findings

Contact Info

Product

Resources

About