Skip to main content
. 2023 Jun 16;13:1179025. doi: 10.3389/fonc.2023.1179025

Figure 1.

Figure 1

Overview of the proposed method: The WSI are divided into patches to boost the dataset and localize cancer detection. With a pre-trained ResNet50 model, the convolutional features are extracted for each patch and used to train an XGBoost classifier for patch-level classification. Grad-CAM++ on a pre-trained DenseNet169 model calculates the regional importance map for the DUV WSI. The patch-level classification results are merged with the regional importance map in a decision fusion for the WSI-level prediction.