National Natural Science Foundation of China; Research Project of Education Department of Hunan Province [18C0413, 20C1632, 20C1597]; [62071213]
机构署名：
本校为第一且通讯机构
院系归属：
电气工程学院
摘要：
A deep framework for the accelerated multislice magnetic resonance imaging (MRI) reconstruction is proposed here. It exploits the non‐local interslice correlation information between adjacent slices in MRI image sequences to reconstruct high‐quality undersampled MRI images. A novel texture Transformer architecture for MRI reconstruction is designed. Such a framework enables united feature learning across target slice and adjacent slices, which encourages the exploration of deep features and transferring of accurate texture features across adj...
