Skip to main content

Table 6 Statistical results for the multi segmentor

From: COVID-19 lung CT image segmentation using deep learning methods: U-Net versus SegNet

Net.

Class

Sens.

Spec.

Dice.

G-mean

F2

SegNet

\({\hbox {C}}_1\)

0.638

.0.952

0.479

0.780

0.562

\({\hbox {C}}_2\)

0.672

0.965

0.454

0.806

0.564

\({\hbox {C}}_3\)

0.574

0.988

0.121

0.753

0.231

U-NET

\({\hbox {C}}_1\)

0.804

0.930

0.483

0.865

.0.636

\({\hbox {C}}_2\)

0.694

0.983

0.597

0.826

0.652

\({\hbox {C}}_3\)

0.684

0.993

0.225

0.824

0.377

  1. Bold values indicate the highest number of a comparable set
  2. SegNet and U-NET multi class segmentation tools results is terms of sensitivity, specificity, dice, G-mean, and F2 score. Matching color rows display the results for the same class