Reconstruction of cardiac cine MR images using analytic image and neural networks

A reconstruction method for cardiac cine magnetic resonance images is proposed that is based on the combined use of the notion of analytic image and neural network based learning. The analytic image is used to exploit spectral or k-space information and the neural network for a better estimation of missing temporal information. The results show that the proposed approach allows a 4-factor reduction of the data acquisition time in cardiac cine imaging while keeping a good image reconstruction quality with preserved myocardial border sharpness and spatial resolution.