Skip to main content

Table 3 Results of unenhanced radiomics model and triphasic radiomics model predictive ability for distinguishing between iMAD and LPA

From: CT-based radiomics nomogram for differentiation of adrenal hyperplasia from lipid-poor adenoma: an exploratory study

Model

AUC (95% CI)

Sensitivity (%)

Specificity (%)

Accuracy (%)

Cut-off

Unenhanced radiomics model

Training cohort

0.916 (0.826–0.968)

88.6

91.9

90.3

 > 0.513

Testing cohort

0.860 (0.704–0.953)

78.6

72.7

72.2

External validation cohort

0.838 (0.687–0.935)

75.0

80.0

77.5

Triphasic radiomics model

Training cohort

0.964 (0.892–0.994)

91.4

91.9

93.1

 > 0.483

Testing cohort

0.880 (0.728–0.964)

78.6

86.3

80.6

External validation cohort

0.843 (0.693–0.938)

80.0

80.0

77.5

  1. AUC Area under the receiver operator characteristic curve, 95% CI 95% Confidence interval