J-resolved 1H-MRSI offers several unique advantages but suffers from long acquisition time and lmited SNR, especially for longer TEs. Leveraging the recent progress on constrained MRSI reconstruction using learned nonlinear low-dimensional representations, we propose here a new method for SNR-enhancing reconstruction from rapidly generated, noisy J-resolved data, that can computationally efficiently enforce an accurate nonlinear low-dimensional representation of high-dimensional J-resolved spectroscopic signals through a learned network-based project as well as complementary spatial constraints. The proposed method has been shown to improve the SNR significantly for in vivo J-resolved 1H-MRSI of the brain.
This abstract and the presentation materials are available to members only; a login is required.