Skip to main content

Table 4 Area under the curve (AUC), accuracy, sensitivity, and specificity achieved with the validation set in the classification of lesions versus normal tissue and malignant versus benign solid lesions using the full texture feature set and the reduced feature set

From: Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study

Sub-dataset AUC (95% confidence interval) Accuracy (%) Sensitivity (%) Specificity (%)
Lesions versus normal tissue
 Full feature set 0.96 (0.89–0.98) 93.3 92.6 94.1
 Reduced feature set 0.98 (0.92–0.99) 94.4 96.3 92.1
Malignant versus benign lesions
 Full feature set 0.98 (0.81–0.99) 90.7 85.2 96.3
 Reduced feature set 0.96 (0.90–0.99) 87.1 81.5 92.6