Table 4 Performance of the CBAM ResNet-18 in test dataset.

From: An assessment of breast cancer HER2, ER, and PR expressions based on mammography using deep learning with convolutional neural networks

 

HER2

ER

PR

AUC (95%CI)

0.708 (0.609, 0.808)

0.785 (0.673, 0.897)

0.706 (0.603, 0.809)

Recall

0.800

0.865

0.684

Specificity

0.613

0.727

0.687

Accuracy

0.651

0.845

0.678

Precision

0.394

0.948

0.889

F1-score

0.528

0.905

0.773

Back to article page