Skip to main content

Table 2 Diagnostic Performances of Different Network Structures on 5-Fold Cross-Validation

From: Deep learning based on ultrasound images to predict platinum resistance in patients with epithelial ovarian cancer

AUCs

Fold 1

Fold 2

Fold 3

Fold 4

Fold 5

Mean AUC

ResNet34

0.86

0.68

0.78

0.88

0.71

0.78 ± 0.08

DenseNet121

0.86

0.88

0.70

0.85

0.78

0.81 ± 0.07

Swin Transformer

0.72

0.67

0.81

0.81

0.73

0.75 ± 0.05

ConvNext

0.86

0.88

0.87

0.87

0.85

0.87 ± 0.01

  1. AUC, area under the receiver operating characteristic curve
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us