Skip to main content
Fig. 5 | Cancer Imaging

Fig. 5

From: Application of a machine learning method to whole brain white matter injury after radiotherapy for nasopharyngeal carcinoma

Fig. 5

ROC curves of the SVM classifier. The orange broken line corresponds to the ROC curve of the SVM classifier for 0–6 months post-RT versus the control; the purple broken line, for 6–12 months post-RT versus the control; and the sky-blue real line, for > 12 months post-RT versus the control. A yellow, pea green or purple diamond on the curve corresponds to the classification rate, with zero as the classification threshold. AUC = area under the curve. This figure shows that our classifier had a better classification performance

Back to article page