Skip to main content
. Author manuscript; available in PMC: 2020 Mar 1.
Published in final edited form as: IEEE Trans Med Imaging. 2019 Mar;38(3):686–696. doi: 10.1109/TMI.2018.2870343

Fig. 5.

Fig. 5.

Box-and-whisker plots of ROI-based AUC performance on the DBT test set while varying the simulated mammography training sample size available for stage 1 C1-frozen transfer learning. (a) Stage 1 mammogram-trained C1-frozen CNN without stage 2 (scheme A in Fig. 2). (b) Stage 2 C1-frozen transfer learning at a fixed (100%) DBT training set size (scheme B). (c) Stage 2 C1-to-F4-frozen transfer learning at a fixed (100%) DBT training set size (scheme C). The dotted line in (a) to (c) plots the mean AUC at each simulated training set size. Note that the plots in (a) to (c) use categorical x-axis to show details of the low percentage region. (d) shows the mean and standard deviation of AUC in (a) to (c) together with the x-axis plotted in a linear scale.