… sCT generation, we trained the 2D CycleGAN using the deformation-registered CT-iCBCT
slicers and generated the sCT with corresponding iCBCT image … of each layer of the image, …

… the resulting sCT with the original CBCT using the deformed … Through the last two convolutional
layers with kernel size of … , CycleGAN USsCT and proposed USsCT images from four …

… MR images using deformable registration, and the deformed CT (dCT) … The 2.5D CycleGAN
was constructed to generate sCT from … The weights and biases in the layers were trained by …

… model parameters in shallower layers to be updated mostly … , we deformed the planning
CT to the 5 fraction CBCTs. The … attention cycleGAN method for CBCT to sCT generation. The …

… layers to preserve spatial information. Our model was adapted to segment volumetric data
(3D … This study demonstrated that the use of CycleGAN-generated sCT images to enhance …

… sCT generated by CycleGAN showed better structural consistency with CBCT. On the other
hand, the sCT was obtained from … at both ends could not contain complete images of the layer…

… were compared to deformed structures from the planning CT (… network (cycle-GAN)-based
CBCT-to-sCT conversion algorithm for … Thirdly, transform layers were added into the original …

… acquired using deformable image registration, which uses … All convolutional layers use
instance normalization and the … is the HU value of sCT generated by Cycle-GAN, and the green …

… However, the output layer used the Tanh nonlinearity to scale image intensity … CycleGAN-best
sCT images, both image sets were deformably registered to the pCT using the Deformable …

… last layer of the content mask was a 7 × 7 convolution layer … copied to deformed CT images,
CBCT and sCT images in the … The image quality indices of sCT generated from cycleGAN …