… improve accuracy of full reconstruction image (ie, refining … MRI method employing a
cyclic loss with fully residual convolutional GANs that achieved real-time performance (reconstruction …

… combined compressed sensing and parallel imaging can be … 17.7 to 4.7 s without substantial
loss of image quality (figure … -sharing to reconstruct 25 phases throughout the cardiac cycle. …

… acquisition process in MRI, this premise is often violated and leads to a loss in image … CS
reconstruction, timeframes during rapid motion of the heart at the beginning of the cardiac cycle …

… ) and cyclic loss [24]. Similar to the GAN theory, adversarial loss and content loss including
both … The reconstruction network structure, loss function are described in detail in this section. …

… , compressed sensing and deep generative model are combined for MRI images reconstruction.
… using a generative adversarial network with a cyclic loss. IEEE Transactions on medical …

… We observe superior reconstruction performance with the … fixed; we systematically cycle
through these subproblems until … We specifically observe loss of important borders and temporal …

… (27) proposed a patch-based CS technique (“LOST,” see next section) to acquire and
reconstruct isotropic spatial … LOST reconstruction was performed inline (via CPU cluster) in ~ 1 h. …

… Cyclic Loss for network training. Deora et al. [22] used a combination of patch-based discriminator
and loss … To better improve the reconstruction quality, we add image domain loss and …

… k-space loss function to avoid highfrequency information loss. For … Jeong, “Compressed
sensing mri reconstruction using a … with a cyclic loss,” IEEE transactions on medical imaging, vol. …

… Recently, compressed sensing MRI has been approved by the FDA for GE and … Jeong,
“Compressed sensing MRI reconstruction using a generative adversarial network with a cyclic loss…