公开(公告)号：US20250061618A1

公开(公告)日：2025-02-20

申请号：US18720261

申请日：2022-12-14

Applicant: REGENTS OF THE UNIVERSITY OF MINNESOTA

Inventor： Steen MOELLER ,  Mehmet AKÇAKAYA ,  Kamil UGURBIL

IPC: G06T11/00 ,  G01R33/56 ,  G06T5/70

Abstract: Denoised magnetic resonance images are generated using a two-step process. An initial set of images is first denoised on a per channel basis using a locally low-rank-based denoising technique. The denoised coil channel images are transformed back into k-space and the denoised k-space data are then applied to a nonlinear image reconstruction. In some instances, the nonlinear image reconstruction can be implemented using a trained neural network. The neural network may be trained using a self-supervised learning technique.