MRI partial Fourier deep learning reconstruction with implicit phase constraint

Motivation: Partial Fourier deep learning for under-sampled k-space reconstruction has not been well studied, it is worth investigating to combine the two methods to achieve better parallel imaging. Goal(s): To achieve better partial Fourier reconstruction empowered by deep learning. Approach: A deep learning reconstruction network with implicit phase constraint for partial Fourier imaging was proposed. Results: The proposed method achieves better IQ in multi-anatomy compared to conventional partial Fourier reconstruction method. Impact: Our method integrates implicit phase constraint into partial Fourier deep learning reconstruction network, it has been proved that the method works well in multi-anatomy, and it is expected the applications of partial Fourier with deep learning reconstruction can be expanded.