Skip to main content

Table 5 The performances of the models in predicting MVI

From: Using pre-operative radiomics to predict microvascular invasion of hepatocellular carcinoma based on Gd-EOB-DTPA enhanced MRI

 

Training set

Validation set

AUC

95% CI

Sen (%)

Spe (%)

P value

AUC

95% CI

Sen (%)

Spe (%)

P value

Clinicoradiological model

0.715

0.678–0.745

51.88

91.67

0.003

0.708

0.677–0.719

50.33

92.07

0.041

Radiomics model

0.782

0.734–0.801

63.71

82.80

0.012

0.755

0.721–0.786

84.50

80.78

0.012

Combined model

0.841

0.822–0.867

81.43

72.76

0.007

0.826

0.798–0.838

90.89

69.85

0.026

  1. AUC area under the ROC curve, CI confidence interval, Sen sensitivity, Spe specificity
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us