Synthesized 7T MRI from 3T MRI via deep learning in spatial and wavelet domains.

•We introduce a novel method for 7T image synthesis by leveraging complementary information of both spatial and wavelet domains.•We provide an efficient way to incorporate image priors in deep learning to achieve superior image synthesis performance.•We present a flexible and parameter-efficient WAT layer that can be embedded into a neural network to facilitate effective reconstruction with consideration of multiple frequency components.