Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning

NEUROCOMPUTING

卷:174

Article

Wang, Zhe¹  Li, Hongsheng¹  Yuan, Jing²  Wang, Xiaogang¹ 

[1] Chinese Univ Hong Kong, Dept Elect Engn, Shatin, Hong Kong, Peoples R China

[2] Chinese Univ Hong Kong, Dept Imaging & Intervent Radiol, Shatin, Hong Kong, Peoples R China

关键词: Magnetic Resonance Fingerprinting;    Compressed sensing;    Metric learning;    Cartesian sampling;   

DOI  :  10.1016/j.neucom.2015.09.077

来源: Elsevier

【 摘 要 】

Magnetic Resonance Fingerprinting (MRF) is a novel technique that simultaneously estimates multiple tissue-related parameters, such as the longitudinal relaxation time T-1, the transverse relaxation time T-2, off resonance frequency B-0 and proton density, from a scanned object in just tens of seconds. However, the MRF method suffers from aliasing artifacts because it significantly undersamples the k-space data. In this work, we propose a compressed sensing (CS) framework for simultaneously estimating multiple tissue-related parameters based on the MRF method. It is more robust to low sampling ratio and is therefore more efficient in estimating MR parameters for all voxels of an object. Furthermore, the MRF method requires identifying the nearest atoms of the query fingerprints from the MR-signal-evolution dictionary with the L-2 distance. However, we observed that the L-2 distance is not always a proper metric to measure the similarities between MR Fingerprints. Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints. Numerical results on extensive simulated cases show that our method substantially outperforms state-of-the-art methods in terms of accuracy of parameter estimation. (C) 2015 Elsevier B.V. All rights reserved.

【 授权许可】

Free