Enhanced Magnetic Resonance Imaging-Based Knee Cartilage Segmentation Using a Swin-UNet Conditional Generative Adversarial Network: Development and Validation Study.

Notably, for tibial cartilage, UNet-cGAN showed a statistically significant improvement over plain UNet, whereas the difference between the proposed Swin-UNet cGAN and UNet, although numerically larger, did not reach statistical significance.

also in 111,027 other papers