Skip to main content

Table 1 Normalized confusion matrix of automated image segmentation on the synthesized Ecad-stained cross section images. The overall prediction accuracy measured by the sum of diagonal elements was 0.9582.

From: Automated recognition of cell phenotypes in histology images based on membrane- and nuclei-targeting biomarkers

True class

Predicted class

 

E1

E2

E3

E4

E5

total

E1

0.3457

0.0039

0.0000

0.0001

0.0000

0.3498

E2

0.0014

0.2832

0.0007

0.0062

0.0004

0.2919

E3

0.0000

0.0008

0.0426

0.0008

0.0000

0.0441

E4

0.0000

0.0000

0.0009

0.2270

0.0122

0.2400

E5

0.0001

0.0024

0.0001

0.0120

0.0596

0.0742

Total

0.3472

0.2902

0.0443

0.2461

0.0722

1.0000

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us