Computed tomographic virtual colonoscopy computer-aided polyp detection in a screening population

Abstract

Background & aims: The sensitivity of computed tomographic (CT) virtual colonoscopy (CT colonography) for detecting polyps varies widely in recently reported large clinical trials. Our objective was to determine whether a computer program is as sensitive as optical colonoscopy for the detection of adenomatous colonic polyps on CT virtual colonoscopy.

Methods: The data set was a cohort of 1186 screening patients at 3 medical centers. All patients underwent same-day virtual and optical colonoscopy. Our enhanced gold standard combined segmental unblinded optical colonoscopy and retrospective identification of precise polyp locations. The data were randomized into separate training (n = 394) and test (n = 792) sets for analysis by a computer-aided polyp detection (CAD) program.

Results: For the test set, per-polyp and per-patient sensitivities for CAD were both 89.3% (25/28; 95% confidence interval, 71.8%-97.7%) for detecting retrospectively identifiable adenomatous polyps at least 1 cm in size. The false-positive rate was 2.1 (95% confidence interval, 2.0-2.2) false polyps per patient. Both carcinomas were detected by CAD at a false-positive rate of 0.7 per patient; only 1 of 2 was detected by optical colonoscopy before segmental unblinding. At both 8-mm and 10-mm adenoma size thresholds, the per-patient sensitivities of CAD were not significantly different from those of optical colonoscopy before segmental unblinding.

Conclusions: The per-patient sensitivity of CT virtual colonoscopy CAD in an asymptomatic screening population is comparable to that of optical colonoscopy for adenomas > or = 8 mm and is generalizable to new CT virtual colonoscopy data.

Figure 1

Free-response receiver operating characteristic (FROC) curves. FROC curves for the training (open markers) and test (filled markers) sets are shown for adenomatous polyps 10 mm or larger (circles), 8 mm or larger (squares), and 6 mm or larger (triangles). Shown are pooled data from all three medical centers. We show only the clinically relevant portion where the number of false positives (FP) per patient is below 10. Error bars (one standard deviation) from bootstrap analysis of sensitivity and false-positive rate are shown at the three operating points for the test set from Table 3.

Figure 2

(A) Optical and (B, C) three-dimensional virtual colonoscopy images of 1.4 cm polyp in the transverse colon of a 64 y.o. female in the test set The blue coloring in (C) indicates the part of the polyp detected by CAD. A portion of the colon centerline is shown in green in (B, C).

Figure 3

(A) Optical and (B, C) three-dimensional virtual colonoscopy images of 0.8 cm polyp in the sigmoid colon of a 60 y.o. male in the test set The blue coloring in (C) indicates the part of the polyp detected by CAD. A portion of the colon centerline is shown in green in (B, C).

Figure 4

(A) Optical and (B, C) three-dimensional virtual colonoscopy images of 0.6 cm polyp in the transverse colon of a 65 y.o. male in the test set The blue coloring in (C) indicates the part of the polyp detected by CAD. A portion of the colon centerline is shown in green in (B, C).