Table 1 Performance measures for the ConvNet classifier on the TCGA (pathological, N = 195) and NC (normal, N = 21) data cohorts.

From: Accurate and reproducible invasive breast cancer detection in whole-slide images: A Deep Learning approach for quantifying tumor extent

Data set

Dice

PPV

NPV

TPR

TNR

FPR

FNR

TCGA

0.7586 ± 0.2006

0.7162 ± 0.2204

0.9677 ± 0.0511

0.8691 ± 0.1582

0.9218 ± 0.0764

0.0782 ± 0.0764

0.1309 ± 0.1582

NC

N/A

N/A

1 ± 0

N/A

0.9964 ± 0.0110

0.0036 ± 0.0110

N/A

  1. The measures included Dice, PPV, NPV, TPR, TNR, FPR and FNR. Note that for the normal cases considered, not all the performance measures are shown because the NC data cohort did not have cancer annotations.
Back to article page