Skip to main content
. Author manuscript; available in PMC: 2018 Sep 1.
Published in final edited form as: Mach Learn Med Imaging. 2017 Sep 7;10541:371–378. doi: 10.1007/978-3-319-67389-9_43

Fig. 2. Scatter plots of F-recall and actual FAIL case percentage vs. proportion of predicted FAIL cases on test datasets.

Fig. 2

Left: F-share vs F-recall. Right: Fail F-share vs FAIL percentage. Mark size shows the dataset size. Mark shape represents dataset (site): ○ - CODE-Berlin (N=176); □ - Münster (N=1033); △ - Stanford (N=105); ▽ - Houston (N=195).