Premium
Accelerating T 2 mapping of the brain by integrating deep learning priors with low‐rank and sparse modeling
Author(s) -
Meng Ziyu,
Guo Rong,
Li Yudu,
Guan Yue,
Wang Tianyao,
Zhao Yibo,
Sutton Brad,
Li Yao,
Liang ZhiPei
Publication year - 2021
Publication title -
magnetic resonance in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.696
H-Index - 225
eISSN - 1522-2594
pISSN - 0740-3194
DOI - 10.1002/mrm.28526
Subject(s) - prior probability , artificial intelligence , computer science , human connectome project , compressed sensing , pattern recognition (psychology) , deep learning , image (mathematics) , iterative reconstruction , computer vision , bayesian probability , neuroscience , functional connectivity , biology
Purpose To accelerate T 2 mapping with highly sparse sampling by integrating deep learning image priors with low‐rank and sparse modeling. Methods The proposed method achieves high‐speed T 2 mapping by highly sparsely sampling (k, TE)‐space. Image reconstruction from the undersampled data was done by exploiting the low‐rank structure and sparsity in the T 2 ‐weighted image sequence and image priors learned from training data. The image priors for a single TE were generated from the public Human Connectome Project data using a tissue‐based deep learning method; the image priors were then transferred to other TEs using a generalized series‐based method. With these image priors, the proposed reconstruction method used a low‐rank model and a sparse model to capture subject‐dependent novel features. Results The proposed method was evaluated using experimental data obtained from both healthy subjects and tumor patients using a turbo spin‐echo sequence. High‐quality T 2 maps at the resolution of 0.9 × 0.9 × 3.0 mm 3 were obtained successfully from highly undersampled data with an acceleration factor of 8. Compared with the existing compressed sensing–based methods, the proposed method produced significantly reduced reconstruction errors. Compared with the deep learning–based methods, the proposed method recovered novel features better. Conclusion This paper demonstrates the feasibility of learning T 2 ‐weighted image priors for multiple TEs using tissue‐based deep learning and generalized series‐based learning. A new method was proposed to effectively integrate these image priors with low‐rank and sparse modeling to reconstruct high‐quality images from highly undersampled data. The proposed method will supplement other acquisition‐based methods to achieve high‐speed T 2 mapping.