Skip to main content
. 2023 Jun 8;13(7):4447–4462. doi: 10.21037/qims-22-1114

Figure 2.

Figure 2

Illustration of our network. The network takes the 18F-FDG PET/MR slices as parallel input, and the output is the segmented mask. The U-net architecture performed multiscale feature extraction and fusion for 18F-FDG PET/MR images, facilitating accurate segmentation. FDG, fluorodeoxyglucose; MR, magnetic resonance; PET, positron emission tomography.