Skip to main content
Fig. 3 | Cancer Imaging

Fig. 3

From: Identifying factors that may influence the classification performance of radiomics models using contrast-enhanced mammography (CEM) images

Fig. 3

Random forest (RF) radiomics model classification results for 100 rounds of cross-validation. The blue dashed line is the cutoff line for a misclassification probability of 0.05, and the red dashed line is the cutoff line for a misclassification probability of 0.20 for benign and malignant lesions. The average AUC, accuracy, sensitivity, and specificity values and the standard deviation are 0.915 ± 0.055, 0.880 ± 0.068, 0.878 ± 0.097, and 0.886 ± 0.108

Back to article page