Skip to main content

Table 2 Diagnostic accuracy for significant features differentiating patients with pathologic complete response (pCR) versus non-pCR patients

From: Textural radiomic features and time-intensity curve data analysis by dynamic contrast-enhanced MRI for early prediction of breast cancer therapy response: preliminary data

  p value*ROC-AUCSensitivitySpecificityPPVNPVAccuracyCutoff
Textural featuresΔ Entropy0.0240.710.670.730.560.810.713.78
Δ LRE0.0210.710.730.700.550.840.710.57
Δ Busyness0.0200.720.670.800.630.830.7634.38
Dynamic featuresΔ MSD0.0130.740.670.830.670.830.7827.74
Δ WIS< 0.0010.730.600.870.690.810.7873.62
Δ WOS0.0120.860.870.800.680.920.8224.42
SIS< 0.0010.930.930.870.780.960.8956.47
  1. LRE Long-run emphasis, MSD Maximum signal difference, NPV Negative predictive value, PPV Positive predictive value, ROC-AUC Receiver operating characteristic area under the curve, SIS Standardised index of shape, WIS Washin, WOS Washout slope
  2. *Kruskal-Wallis test