Skip to main content

Table 2 Best classification performance on BCDR database

From: A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis

  Normal/AbnormalBenign/Malignant
Embedded MethodAUC98.16 (97.87−98.48)92.08 (91.61−92.58)
 Accuracy97.31 (96.92−97.31)88.46 (87.69−89.23)
 Sensitivity94.62 (93.85−94.62)89.09 (87.27−90.91)
 Specificity100 (100−100)88.00 (86.67−89.33)
Filter MethodAUC98.67 (98.57−98.76)92.13 (91.66−92.78)
 Accuracy96.92 (96.54−96.92)87.69 (86.92−89.23)
 Sensitivity93.85 (93.85−94.62)89.09 (87.27−90.91)
 Specificity99.23 (99.23−100)87.33 (85.33−89.33)
  1. The classification performance calculated in correspondence with the best result highlighted in the 100 rounds of 10-fold cross-validation for increasing the number of selected features, are summarized. We tested the significance of the diversity of performance measures obtained with the two different feature selection techniques on the same classification problem. Statistical significance is measured with the Wilcoxon-Mann-Whitney test: ** p-value <0.01 (Bonferroni correction)