Skip to main content

Table 3 Diagnostic performance of DTI parameters in discriminating recurrent breast cancer from postoperative changes

From: Prediction of local breast cancer recurrence after surgery: the added value of diffusion tensor imaging

Feature

Sensitivity (%)

Specificity (%)

AUC

PPV (%)

NPV (%)

Accuracy (%)

F1 score (%)

MCC (%)

MD ≤ 1.18

97.1

88.1

0.934

87.2

97.4

92.2

91.9

84.9

AD ≤ 1.95

85.7

83.3

0.875

81.1

87.5

84.4

83.3

68.8

RD ≤ 1.5

88.6

73.8

0.836

73.8

88.6

80.5

80.5

62.4

FA ≥ 0.39

77.1

83.3

0.835

79.4

81.4

80.5

78.3

60.6

RA ≥ 0.27

31.4

83.3

0.542

61.1

59.3

59.7

41.5

17.4

  1. AUC = Area under the ROC curve, PPV = positive predictive value. NPP = negative predictive value Accuracy = (TP + TN)/(all Positive + all Negative). F1 = 2TP/(2TP + FP + FN). MCC = Matthews Correlation Coefficient = TP*TN − FP*FN / sqrt (TP + FP) *(TP + FN) *(TN + FP) *(TN + FN)). MD, AD and, RD cutoff values were given in × 10−3 mm2/s