Data augmentation for deep learning based
accelerated MRI reconstruction with limited data
Zalan Fabian 1 Reinhard Heckel 2 Mahdi Soltanolkotabi 1
Abstract tients. Due to the subsampling, there are fewer equations
Deep neural networks have emerged as very suc- than unknowns, and therefore the signal is not uniquely iden-
cessful tools for image restoration and reconstruc- tifiable from the measurements. To overcome th ...


雷达卡




京公网安备 11010802022788号







