Fig. 1
From: A deep-learning approach for segmentation of liver tumors in magnetic resonance imaging using UNet++
Automated segmentation process. To make masks, the MR arterial phase and T2 images of each patient were extracted from the training set and were manually delineated layer by layer to identify the liver and tumor. Ground truth is provided by these masks. A model for automatic delineation is trained based on the ground truth. Next, the validation and test sets were assembled and input in the trained model, and finally layer by layer, the images with masks were obtained