Magnetic resonance image reconstruction using similarities learnt from multi-modal images
Yingkun Hou ( Taishan University)
Fan Lam ( University of Illinois at Urbana-Champaign)
- 物理技术－会议论文 
Compressed sensing has shown great potential to speed up magnetic resonance imaging (MRI) assuming the image is sparse and compressible in a transform domain. Conventional methods typically use a pre-defined patch-based nonlocal operator (PANO) to model the sparsity between image patches. The linearity of PANO allows us to establish a general formulation to reconstruct magnetic resonance image from undersampled data and provides feasibility to incorporate prior information learnt from guide images. To demonstrate the feasibility and performance of PANO, learning similarities from multi-modal images are presented to significantly improve the reconstructed images over conventional redundant wavelets in terms of visual quality and reconstruction errors.
CitationIEEE China Summit and International Conference on Signal and Information Processing-ChinaSIP'13, 6th-10th , July, 2013, pp.264-268.
The following license files are associated with this item: