Curriculum learning based overcomplete u-net for liver tumor segmentation from computed tomography images

HIGHLIGHTS

• who: U-Net architecture et al. from the School of Computer Science and Engineering, VIT-AP University Amaravati, Andhra Pradesh, India have published the article: Curriculum learning based overcomplete U-Net for liver tumor segmentation from computed tomography images, in the Journal: (JOURNAL) of Aug/30,/2022
• what: To perform liver tumor segmentation directly from the CT images, we have presented a curriculum learning-based U-Net with two branches: overcomplete and undercomplete.
• how: The samples from three levels of data are shown in Figure 2. - Stage 1 easy images (collected images that . . .
  

   

  

  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.