The following table or figure may be downloaded to PowerPoint for personal use in teaching and presentations. This feature is available to all subscribers to the journal.

You MUST read and follow the guidelines at Request to Reproduce AJR Content if you are distributing or using AJR content beyond academic use (limited distribution, non-revenue producing, or educational purposes).

(Downloading may take up to 30 seconds.
If the slide opens in your browser, select File -> Save As to save it.)
Click on image to view larger version.

Fig. 1B —Free-response receiver operating characteristic (FROC) curves for external validation (diamonds) and previously reported internal validation training (triangles) and testing data sets (squares). Curves show the trade-off in sensitivity per adenomatous polyp versus number of false-positive findings per patient as tunable threshold is varied in computer-aided detection (CAD) software. Circles indicate operating points used to determine sensitivities in Table 1. Graph shows FROC curves for adenomatous polyps 6–9 mm in diameter. Sensitivity of CAD in external validation data set is greater than for both previously reported internal validation data sets.