VS-Net unrolls variable splitting optimization into an end-to-end trainable network for accelerated parallel MRI reconstruction and reports improved accuracy and perceptual quality over prior deep learning methods on knee images at 4x and 6x acceleration.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VS-Net: Variable splitting network for accelerated parallel MRI reconstruction
VS-Net unrolls variable splitting optimization into an end-to-end trainable network for accelerated parallel MRI reconstruction and reports improved accuracy and perceptual quality over prior deep learning methods on knee images at 4x and 6x acceleration.