Table 2 Segmentation performance of the trained SegNet.

From: Deep learning-based quantitative estimation of lymphedema-induced fibrosis using three-dimensional computed tomography images

Class

Accuracy

IoU

MeanBFScore

DSC (F1 score)

Air

0.999

0.999

0.999

0.999

Muscle/Water

0.970

0.947

0.893

0.973

Fat

0.873

0.816

0.921

0.899

Skin

0.957

0.871

0.995

0.931

Fibrosis

0.776

0.584

0.868

0.738

Back to article page