Efficacy of Computer-aided Detection as a Second Reader for 6–9-mm Lesions at CT Colonography: Multicenter Prospective Trial

Abstract

efficacy of computer-aided Detection as a second reader for 6-9-mm lesions at cT colonography: Multicenter Prospective Trial 1 Purpose:To assess the effect of computer-aided detection (CAD) as a second reader on the sensitivity and specificity of computed tomographic (CT) colonography in detecting 6-9-mm colorectal cancer (CRC) lesions. Materials and Methods:Individuals with clinical indications for colonoscopy-either for symptoms or as part of participating in a surveillance program or CRC screening-were prospectively enrolled at one of 10 academic centers between July 2007 and May 2009. Institutional review board approval was obtained at each clinical site, and all participants provided written informed consent. All participants underwent CT colonography and colonoscopy on the same day. Experienced readers interpreted the CT colonography images unassisted and then reviewed all colorectal lesion-like structures pinpointed by the CAD algorithm. Segmental unblinding of CT colonoscopy findings at colonoscopy was utilized. The sensitivity and specificity of unassisted and CAD-assisted reading in identifying individuals with 6-9-mm lesions were calculated and compared by means of pairwise analysis. Results:A total of 618 participants (mean age, 57.9 years; 54.5% male) were included in the final analysis. Of these participants, 464 (75.1%) had no lesions 6 mm or larger, and 52 (8.4%) had 6-9-mm lesions. The sensitivity of CT colonography with unassisted reading and that with CADassisted reading in identifying individuals with 6-9-mm lesions was 65.4% (95% confidence interval [CI]: 50.9%, 78.0%) and 76.9% (95% CI: 63.2%, 87.5%; P = .016), respectively. No significant change in specificity was observed: The specificity of CT colonography with unassisted and that with CAD-assisted reading was 91.8% (95% CI: 88.9%, 94.1%) and 90.9% (95% CI: 88.0%, 93.4%; P = .063), respectively. Evaluation of CAD candidates required an additional 1.6 minutes (25th-75th percentile: 1.0 minute to 3.4 minutes). Conclusion:The addition of CAD to reading performed by experienced readers resulted in a significant benefit in the detection of 6-9-mm polyps at CT colonography in this cohort.q RSNA, 2012 Supplemental material: http://radiology.rsna.org/lookup /suppl

The effect of computer-aided detection markers on visual search and reader performance during concurrent reading of CT colonography

“…Strictly speaking, interpretation of CAD marks simultaneously with unannotated regions of the colon should only happen during a "concurrent" reading paradigm [5,16]. In contrast, during a "second-read" paradigm, CAD is activated only after a full unaided interpretation has been performed, in which case the reader's gaze can jump directly from one CAD mark to another [3,4,17]. Therefore, the second-reader paradigm should avoid the problem of gaze being distracted by markers, since CAD is not used during the initial read and only CAD markers need be inspected during the second component.…”

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

“…Nevertheless, on average, reading times are substantially less than those for optical colonoscopy (21)(22)(23). Multiple CT colonography trials with CAD have shown improved reader times, particularly for inexperienced readers, although the use of CAD in secondary mode has been shown to add about 1-3 minutes to the reading time for most cases (24)(25)(26)(27). The increased sensitivity for polyp detection is accompanied by a small decrease in specificity because, often, possible polyps according to CAD are not true polyps (a CAD false-positive result), which can contribute to reader false-positive results.…”

Errors in CT colonography

“…Computer-aided detection is designed to decrease errors of detection by identifying and directing the reader to polyp-candidates for further characterization. Several studies have demonstrated increased sensitivity for polyp detection accompanied by a relatively small decrease in specificity due to CAD false-positives which can contribute to reader false-positive results [21][22][23][24].…”