Table 3 Model performance in different tumor pathology images.

From: Enhanced digital pathology image recognition via multi-attention mechanisms: the MACC-Net approach

Model

Accuracy

Recall

DSC

40×

TNBC

40×

TNBC

40×

TNBC

SegNet

0.968

0.957

0.887

0.801

0.783

0.761

Swin-Unet

0.976

0.763

0.923

0.856

0.822

0.735

CE-Net

0.945

0.921

0.832

0.876

0.739

0.731

MACC-Net

0.981

0.972

0.931

0.886

0.847

0.823

Back to article page