Table 4.
Feature | AUC (95% CI) | p* | Sensitivity (%) | Specificity (%) | PPV (%) | NPV (%) | OR | p# |
---|---|---|---|---|---|---|---|---|
Texture features | ||||||||
Pre sum entropy 16 bins | 0.80 (0.62–0.79) | <0.001 | 70 | 84 | 58 | 90 | 5.51 | 0.028 |
Pre entropy 64 bins | 0.77 (0.69–0.96) | 0.002 | 90 | 63 | 43 | 95 | 3.28 | 0.033 |
LAP information measure of correlation 1 64 bins | 0.77 (0.57–0.97) | 0.043 | 89 | 71 | 50 | 95 | 3.23 | 0.043 |
LAP information measure of correlation 2 64 bins | 0.77 (0.60–0.93) | 0.009 | 89 | 71 | 50 | 95 | 0.32 | 0.009 |
LVP information measure of correlation 2 64 bins | 0.75 (0.58–0.91) | 0.019 | 78 | 77 | 50 | 92 | 0.31 | 0.019 |
HBP information measure of correlation 1 64 bins | 0.78 (0.60–0.95) | 0.016 | 57 | 100 | 100 | 89 | 0.24 | 0.016 |
Other features | ||||||||
Size (≥ 5 cm) | 0.76 (0.57–0.59) | 0.004 | 82 | 82 | 54 | 90 | 3.01 | 0.004 |
p value from AUC
p value from logistic regression
Area under the curve (AUC) values from ROC analysis and odds ratios (OR) from logistic regression analysis are shown
AUC = area under the curve; HBP = hepatobiliary phase, LAP = late arterial phase, LVP = late venous phase; NPV = negative predictive value; OR = odds ratio; PPV = positive predictive value