Synthetic ct generation based on cbct using improved vision transformer cyclegan

HIGHLIGHTS

• What: The authors test the proposed method in two datasets provided by a cooperative tertiary hospital. Recognizing the stability of organ positions and reduced tissue mobility during data acquisition, the authors leveraged the open-source advanced normalization tools (ANTs) for affine registration, with the primary objective of ensuring alignment between each CBCT and CT pair for the purpose of model test. The aim of sCT is to serve as a foundation for subsequent clinical tasks, particularly dose calculation. This study proposes an unsupervised learning model, IViT-CycleGAN, aiming to synthesize sCT from CBCT for future clinical practice . . .
  

   

  

  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.