Skip to main content

Table 5 Performance of the individual parameters measured from ROC curves (based on the Youden index for determining cut-offs)

From: Texture analysis on MR images helps predicting non-response to NAC in breast cancer

   Se (%)  Sp (%)  AUC  Cut-offs
Energya 64 79 0.702 41
Entropya 64 79 0.696 182
Contrast 30 95 0.576 17
Homogeneitya 58 84 0.701 144
Correlation 62 16 0.512 42
Inv. Diff. Momenta 60 84 0.711 152
Sum average 28 90 0.527 103
Sum variance 78 42 0.583 104
Difference variancea 60 79 0.649 86
SRE 80 42 0.569 0.004
LRE 86 37 0.569 301
GLN 74 42 0.555 621
RLN 38 90 0.579 75
RPa 42 90 0.640 0.740
LGRE 42 90 0.630 0.800
HGREa 42 90 0.644 2.40
SRLGE 70 53 0.582 0.003
SRHGE 16 100 0.510 0.007
LRLGE 80 37 0.536 233
LRHGE 72 58 0.620 781
Amplitude 67 58 0.567 69.1
Wash-out 27 95 0.594 0.09
Wash-ina 86 47 0.685 0.50
Massb 63 46 0.546 _
non Massb 63 46 0.546 _
Ki67 > 14 %b 42 82 0.621 _
HER2 +b 79 44 0.615 _
HR-/HER2 +b 100 20 0.600 _
  1. An overall better performance of GLCM compared to RLM parameters, as well as a better performance of texture and kinetic parameters compared to BI-RADS and biological parameters was observed
  2. aParameters performing significantly better than a random classifier (p(AUC > 0.5) < 0.05)
  3. bCategorial variables without cut-offs