Skip to main content
. 2021 Feb 4;13(4):617. doi: 10.3390/cancers13040617

Figure 1.

Figure 1

Receiver operating characteristic (ROC) and area under the curve (AUC) performance on test data. ROC/AUC performance of the bifocal convolutional neural network (BCNN) for recognition of hematoxylin and eosin (H&E) (A) and immunohistochemical (IHC) (B) features. (C) Comparison of ROC/AUC performance of BCNN with state-of-the-art deep learning methods.