Skip to main content

Table 3 The vessel detection performance and percentage of splits and merges relative to the total number of vessels (n), measured for both datasets in the cross-validation

From: Quantifying the tumour vasculature environment from CD-31 immunohistochemistry images of breast cancer using deep learning based semantic segmentation

 

Behold

Mission

(n = 17940)

(n = 16894)

Precision

0.791

0.776

Recall

0.655

0.727

F1 score

0.717

0.750

merged (%)

2.386

3.344

split (%)

1.048

0.900