Skip to main content
. 2018 May 2;8:6875. doi: 10.1038/s41598-018-25261-7

Figure 5.

Figure 5

(a) Three-fold cross-validation procedure for evaluating classification accuracy. (b) Separation of benign and malignant gland feature vectors during training in 1 of 3 validation trials. (c) Separation of benign and malignant gland feature vectors during validation in 1 of 3 validation trials. (d) ROC curve for the 3 validation trials resulting in a sensitivity of 0.94 and specificity of 0.85 at the optimum operating point.