Paper: | SU-AM-PS3.4 |
Session: | Image Guided Detection and Diagnosis |
Time: | Sunday, April 9, 10:50 - 12:10 |
Presentation: |
Poster
|
Title: |
Comparing Image Detection Algorithms Using Resampling |
Authors: |
Frank W. Samuelson; U.S. Food and Drug Administration | | |
| Nicholas Petrick; U.S. Food and Drug Administration | | |
Abstract: |
Automated detection tools for medical imaging are commonly characterized using free-response receive operating characteristic (FROC) methods. However, few statistical tools are currently available to estimate statistical significance when comparing two FROC performance curves. In this study, we introduce a permutation and a bootstrap resampling method for the nonparametric estimation of statistical significance of performance metrics when comparing two FROC curves. We then provide an initial validation using an area under the FROC performance metric and simulated CD algorithm prompts. Validation is based on a comparison of the Type I error rate produced by two statistically identical CD algorithms. The results of 10000 Monte Carlo trials show that both the permutation and bootstrap methods produced excellent estimates of the expected Type I error rate. |