Skip to main content
. 2019 May 7;32(4):656–664. doi: 10.1007/s10278-019-00226-y

Fig. 3.

Fig. 3

Classification model compared to technologist performance. Classification model and human performance AUC was the same at 0.999 but at the upper left of the AUC, it appears that while humans slightly outperform the model at the lowest false-positive fraction, the model reaches a higher true positive fraction sooner and more consistently