Fig. 7From: Histopathological distinction of non-invasive and invasive bladder cancers using machine learning approachesPrediction accuracy and ROC curves of CNN-based models. Pre-trained VGG16 and VGG19 networks were used to build the models. AUC values of the models were indicated in the caption. Twenty iterations were performed for each model. The mean ROC curve (blue) and standard deviation (grey shade area) are presentedBack to article page