Deep Learning-based MRS Reconstruction with Artificial Fourier Transform Network (AFT-Net)

Motivation: Complex-valued deep neural network has not been fully investigated in MRS reconstruction and preprocessing. Goal(s): We aim to solve the spectroscopy inverse problems in domain transform from FIDs to spectra, especially for accelerated MRS reconstruction. Approach: A complex-valued deep learning framework artificial Fourier transform network (AFT-Net) is proposed to directly reconstruct and process the complex-valued raw data in the sensor domain. Results: Evaluation of different acceleration rates was performed on the in vivo dataset. AFT-Net demonstrated the ability to reconstruct the data under up to 80 times acceleration rate. The proposed AFT-Net is an efficient and accurate approach for MEGA-PRESS MRS accelerated reconstruction. Impact: MRS reconstruction and preprocessing with AFT-Net should be able to determine the domain-manifold mapping and process FID data directly, which shows superior performance compared with numerical method and can be served as an efficient and accurate approach for MRS acquisition.