Skip to main content

Table 3 AUC, Accuracy, specificity, and sensitivity on training and testing sets of different models

From: Radiomics model building from multiparametric MRI to predict Ki-67 expression in patients with primary central nervous system lymphomas: a multicenter study

 

Metrics

ADC + DWI + T1-CE

ADC + DWI

DWI + T1-CE

ADC + T1-CE

ADC

T1-CE

DWI

Training set

AUC

0.878

0.854

0.829

0.740

0.733

0.773

0.783

Accuracy

0.803

0.782

0.732

0.739

0.718

0.725

0.725

Sensitivity

0.686

0.586

0.676

0.643

0.614

0.789

0.676

Specificity

0.917

0.972

0.789

0.833

0.819

0.662

0.775

Testing set

AUC

0.869

0.828

0.795

0.733

0.723

0.679

0.774

Accuracy

0.742

0.710

0.758

0.742

0.710

0.613

0.726

Sensitivity

0.645

0.516

0.645

0.677

0.613

0.677

0.613

Specificity

0.839

0.903

0.871

0.807

0.807

0.548

0.839

  1. AUC area under the curve