Figure 2
From: Automated Classification of Benign and Malignant Proliferative Breast Lesions
The receiver operating characteristic (ROC) curve of our CAFE model of the combined and optimized L1-regularized and early stopping logistic regression algorithms is graphed in blue. This model achieved a V-score AUC of 0.918. The ROC curve of Dong et al.’s model of the L1-regularized logistic regression algorithm is in red. Their model achieved a V-score AUC of 0.858.
