Accelerated Magnetic Resonance Imaging using Non-Fourier Encoding in Parallel Compressive Sensing and Deep learning Frameworks

The main objective of this research is to enhance the performance of CS reconstruction in multi-receive MRI systems by proposing an encoding scheme that has superiority over the conventional Fourier encoding in accelerating data acquisition and preserving the image quality. Then the work accelerates 2D and 3D MR imaging using the spread spectrum encoding matrix and finds an application that will benefit the most from this acceleration. The work also looks at extending the proposed encoding to Deep learning for accelerated MRI reconstruction.