Computer-aided Detection in Computed Tomography Colonography with Full Fecal Tagging: Comparison of Standalone Performance of 3 Automated Polyp Detection Systems

Hein, Patrick A.; Krug, Lasse; Romanò, Valentina; Kandel, Sonja; Hamm, Bernd; Rogalla, Patrik

doi:10.1016/j.carj.2009.10.005

Cited by 11 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, CT colonography software automatically segments the colon and asks the reader to verify. At this time, it is important to note whether any extracolonic gas-filled lumen is included in the segmentation (and, if possible, ing supine and prone series) with a stand-alone performance sensitivity of 93.2% for large polyps (≥10 mm) and 91.8% for small adenomas (6-10 mm), a rate that is comparable to previous reports on CAD system performance (28,29). Sensitivity of the average reader improved with use of CAD by approximately five percentage points in each of the segment-, patient-, and polyp-level analyses, with a smaller decrease in specificity.…”

Section: General Approach To Evaluating Polyp Candidatessupporting

confidence: 62%

CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results

et al. 2014

View full text Add to dashboard Cite

1Computed tomography (CT) colonography is a screening modality used to detect colonic polyps before they progress to colorectal cancer. Computer-aided detection (CAD) is designed to decrease errors of detection by finding and displaying polyp candidates for evaluation by the reader. CT colonography CAD false-positive results are common and have numerous causes. The relative frequency of CAD false-positive results and their effect on reader performance on the basis of a 19-reader, 100-case trial shows that the vast majority of CAD false-positive results were dismissed by readers. Many CAD false-positive results are easily disregarded, including those that result from coarse mucosa, reconstruction, peristalsis, motion, streak artifacts, diverticulum, rectal tubes, and lipomas. CAD false-positive results caused by haustral folds, extracolonic candidates, diminutive lesions (<6 mm), anal papillae, internal hemorrhoids, varices, extrinsic compression, and flexural pseudotumors are almost always recognized and disregarded. The ileocecal valve and tagged stool are common sources of CAD falsepositive results associated with reader false-positive results. Nondismissable CAD soft-tissue polyp candidates larger than 6 mm are another common cause of reader false-positive results that may lead to further evaluation with follow-up CT colonography or optical colonoscopy. Strategies for correctly evaluating CAD polyp candidates are important to avoid pitfalls from common sources of CAD false-positive results.

show abstract

Section: General Approach To Evaluating Polyp Candidatessupporting

confidence: 62%

CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results

et al. 2014

View full text Add to dashboard Cite

show abstract

“…In fact, different CAD systems and different versions of the same CAD algorithm may miss and detect completely different types of lesions and pseudolesions. 5,6 In addition, the performance of one CAD algorithm, with any one specific bowel preparation technique, even when excellent, may not generalize to other preparations. 23 We have obtained data from various centers that acquired CT colonographic examinations under different protocols and, unlike *Based on a consensus evaluation for potential reasons for failed detection.…”

Section: Discussionmentioning

confidence: 98%

“…Used as a second reader, CAD algorithms reduce the number of missed lesions [1][2][3][4] ; however, there are substantial differences in the reported performance of CAD systems that impede a direct comparison of test results for different algorithms. 5,6 Although the American College of Radiology standards do not require the use of tagging when performing CT colonography (CTC), 7 its use is considered by experts as best practice. 8 However, distributing tagging materials to patients as well as the application of tagging immediately after incomplete colonoscopy are challenging; fecal tagging may, therefore, not be generally available and CAD algorithms need to be accurate, regardless of the type of bowel preparation.…”

mentioning

confidence: 99%

Computer-Aided Detection of Colorectal Polyps in CT Colonography With and Without Fecal Tagging

Mang¹,

Bogoni²,

Salganicoff³

et al. 2012

Investigative Radiology

View full text Add to dashboard Cite

show abstract

“…It analyzes the morphology of the colonic mucosal surface for polypoid structures meeting specific size, shape, and attenuation thresholds, which are subsequently displayed to the reader for evaluation. The rate of CAD false-positives has steadily decreased as algorithms have been optimized [40][41][42][43]. Nevertheless, typically a handful of polyp-candidates are identified on a given supine and prone dataset requiring a minimal to moderate amount of problemsolving by the reader.…”

Section: Sources Of False Positivesmentioning

confidence: 99%

Errors in CT colonography

2015

View full text Add to dashboard Cite

CT colonography (CTC) is a colorectal cancer screening modality which is becoming more widely implemented and has shown polyp detection rates comparable to those of optical colonoscopy. CTC has the potential to improve population screening rates due to its minimal invasiveness, no sedation requirement, potential for reduced cathartic examination, faster patient throughput, and cost-effectiveness. Proper implementation of a CTC screening program requires careful attention to numerous factors, including patient preparation prior to the examination, the technical aspects of image acquisition, and post-processing of the acquired data. A CTC workstation with dedicated software is required with integrated CTC-specific display features. Many workstations include computer-aided detection software which is designed to decrease errors of detection by detecting and displaying polyp-candidates to the reader for evaluation. There are several pitfalls which may result in false-negative and false-positive reader interpretation. We present an overview of the potential errors in CTC and a systematic approach to avoid them.

show abstract

Computer-aided Detection in Computed Tomography Colonography with Full Fecal Tagging: Comparison of Standalone Performance of 3 Automated Polyp Detection Systems

Abstract: Standalone CTC-CAD analysis in the selected patient collective showed the 3 systems tested to have a variable but overall promising performance with respect to sensitivity and the FP rate.

Cited by 11 publications

References 22 publications

CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results

CT Colonography with Computer-aided Detection: Recognizing the Causes of False-Positive Reader Results

Computer-Aided Detection of Colorectal Polyps in CT Colonography With and Without Fecal Tagging

Errors in CT colonography

Contact Info

Product

Resources

About