Cartesian under-sampling scheme was commonly applied in fast MRI using a deep neural network to simulate the process of fast image acquisition, however, it might not be optimal at a high under-sampling rate. Alternatively, radial under-sampling scheme was used and its efficiency was compared against that of Cartesian under-sampling scheme for T1- or T2-weighted brain, breast, prostate and cervical MRI data at various under-sampling rates. The quantitative evaluation results demonstrated that radial under-sampling scheme could outperformed Cartesian under-sampling scheme on reducing scan time while achieving comparable or better image quality.
This abstract and the presentation materials are available to members only; a login is required.