Skip to main content
Fig. 2 | Cancer Imaging

Fig. 2

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

Fig. 2

Least absolute shrinkage and selection operator (LASSO) regression 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 0.926 ± 0.047, 0.895 ± 0.061, 0.891 ± 0.085, and 0.908 ± 0.096

Back to article page