Skip to main content
Fig. 3 | BMC Cancer

Fig. 3

From: Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images

Fig. 3

Results of ROC curve analyses. ROC curves obtained by deep learning analysis with axial image, coronal image, and these two images combination models in AlexNet (A), GoogLeNet (B), and ResNet (C) to determine the treatment outcome were presented. The ROC curve obtained by T-stage, clinical stage, and a multivariate clinical model was also shown (D). The highest AUC was obtained with the two images combination model in ResNet (AUC = 0.85)

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us