Smooth robust tensor principal component analysis for compressed sensing of dynamic MRI

作者：

Highlights：

• The unsupervised reconstruction methods for dynamic MRI are briefly summarized.

• A smooth robust tensor principle component analysis (SRTPCA) method is proposed for dynamic MRI reconstruction.

• Numerical experiments on cardiac perfusion and cine datasets show the proposed SRTPCA method outperforms the state-of-the-art ones.

摘要

•The unsupervised reconstruction methods for dynamic MRI are briefly summarized.•A smooth robust tensor principle component analysis (SRTPCA) method is proposed for dynamic MRI reconstruction.•Numerical experiments on cardiac perfusion and cine datasets show the proposed SRTPCA method outperforms the state-of-the-art ones.

论文关键词：Robust tensor principal component analysis,Compressed sensing,Low rank tensor approximation,Tensor total variation,Dynamic magnetic resonance imaging

论文评审过程：Received 29 March 2019, Revised 29 November 2019, Accepted 26 January 2020, Available online 5 February 2020, Version of Record 12 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107252