Automated segmentation of vertebral cortex with 3d u-net-based deep convolutional neural network

HIGHLIGHTS

• who: October et al. from the University of Nebraska-Lincoln, United States have published the article: Automated segmentation of vertebral cortex with 3D U-Net-based deep convolutional neural network, in the Journal: (JOURNAL)
• what: The authors used three loss functions (DiceLoss, Weighted Cross-entropy, HybridLoss) to train and test the 3D U-Net network, and compared the effects of the three loss functions on the experimental results. The FPS is slightly lower than that of Seg Net, but since the main purpose of this experiment is not real-time, it is acceptable. This experiment . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.