Table 2 The predicting performance of group of models in the validation cohort.

From: Machine learning method based on radiomics help differentiate posterior pituitary tumors from pituitary neuroendocrine tumors and craniopharyngioma

Features

Accuracy

Precision

Specificity

Sensitivity

AUC

T1-weighted

0.714

0.769

0.000

0.909

0.593

CE T1-weighted

0.786

0.929

0.778

0.788

0.818

T1-weighted & CE T1-weighted

0.750

0.929

0.778

0.743

0.803

  1. CE, contrast-enhanced, AUC, area under curve.