Table 2 Performance evaluation of deep learning methods for single-cell detection.

From: Spatial interplay of tissue hypoxia and T-cell regulation in ductal carcinoma in situ

Methods

TP

FP

FN

Precision

Recall

F1 score

CONCORD

2582

969

173

0.73

0.62

0.67

SCCNN

3591

1200

564

0.74

0.86

0.80

  1. TP number of true positives, FP numbers of false positive, FN number of false negative, Precision percentage of the results that are relevant \(\frac{{TP}}{{TP + FP}}\), Recall percentage of total relevant results correctly classified by the algorithms \(\frac{{TP}}{{TP + FN}}\), F1 score harmonic mean of precision and recall \(2 \times \frac{{P \times R}}{{P + R}}\).
Back to article page