Diagnostic Value of Machine Learning-Based Quantitative Texture Analysis in Differentiating Benign and Malignant Thyroid Nodules

Figure 2

Evaluation of the model’s performance by 10-fold cross-validation. 10-fold cross-validation first randomly divides all the data into ten parts then holds out 10% of the data for testing. This process is repeated ten times, and then the mean accuracy for the algorithm is calculated.