Table 2:

Optimal thresholds obtained from ROC curves and sensitivity/specificity to predict local failurea

Texture ParameterAUCCutoff PointSensitivity (%)Specificity (%)PPV (%)NPV (%)Accuracy (%)
Histogram
    Mean0.67 (0.54–0.81)>110250.2 (28.2–71.7)82.5 (67.2–92.6)64.773.371.0
    SD0.70 (0.56–0.84)<252.940.9 (20.7–63.7)92.5 (79.6–98.4)74.075.074.2
    Geometric mean0.71 (0.57–0.85)>920.636.4 (17.2–59.3)92.5 (79.6–98.4)72.772.772.6
    Harmonic mean0.71 (0.58–0.85)>243.436.4 (17.2–59.3)95.0 (83.1–99.4)80.073.174.2
    Fourth moment0.69 (0.55–0.83)<4.65e1040.9 (20.7–63.6)92.5 (79.6–98.4)74.075.074.2
GLRL
    SRE0.79 (0.68–0.91)<0.034136.4 (17.2–59.3)95.0 (83.1–99.4)80.073.174.2
    LRE0.80 (0.69–0.91)<0.033263.6 (40.7–82.8)80.0 (64.4–90.9)63.680.074.2
    GLN0.80 (0.69–0.92)<0.040868.2 (45.1–86.1)80.0 (64.4–90.9)65.282.175.8
    RLNb0.82 (0.72–0.92)<0.032977.3 (58.8–87.3)77.5 (54.6–92.2)65.486.177.4
    RP0.71 (0.57–0.84)>433.372.7 (49.8–89.3)65.0 (48.3–79.4)53.381.367.7
    LGRE0.73 (0.60–0.85)>44081.8 (59.7–94.8)62.5 (45.8–77.3)54.686.269.4
    HGRE0.74 (0.61–0.87)>433.954.6 (32.2–75.6)85.0 (70.2–94.3)66.777.374.2
    SRLGE0.72 (0.59–0.86)>444.277.3 (54.6–92.2)37.5 (50.9–81.4)56.784.471.0
  • Note:—LRE indicates long-run emphasis; RP, run percentage; LGRE, low gray-level run emphasis; HGRE, high gray-level run emphasis; PPV, positive predictive value; NPV, negative predictive value; AUC, area under the receiver operating characteristic curve; ROC, receiver operating characteristic.

  • a Numbers in parentheses are 95% confidence intervals.

  • b AUC of the RLN was significantly better than that of mean (P = .022). The differences with other selected texture features were not significant (P > .05).