Meeting Banner
Abstract #3478

K-space refinement method for DL-based MR reconstruction by regularizing k-space null space constraint with auto-calibrated kernel

Kanghyun Ryu1, Cagan Alkan2, and Shreyas S. Vasanawala1
1Radiology, Stanford University, Stanford, CA, United States, 2Electrical Engineering, Stanford, Stanford, CA, United States


In this study, we propose a novel refinement method using auto-calibrated k-space null-space kernel to reduce the k-space errors and enable reconstruction of improved high-frequency image details and textures. The refinement algorithm can be easily plugged in after DL-based reconstructions. We show that our method enables the reconstruction of sharper images with significantly improved high-frequency components measured by HFEN and GMSD while maintaining overall error in the image measured by PSNR and SSIM.

This abstract and the presentation materials are available to members only; a login is required.

Join Here