10 April 2020 in Magnetic Resonance in Medicine
Purpose: To develop a deep learning‐based Bayesian estimation for MRI reconstruction.Methods: We modeled the MRI reconstruction problem with Bayes’s theorem, following the recently proposed PixelCNN++ method. The image reconstruction from incomplete k‐space measurement was obtained by maximizing the posterior possibility. A generative network was utilized as the image prior, which was computationally tractable, and the k‐space data fidelity was enforced by using an equality constraint. The stochastic backpropagation was utilized to calculate the descent gradient in the process of maximum a posterior, and a projected subgradient method was used to impose the equality constraint. In contrast to the other deep learning reconstruction methods, the proposed one used the likelihood of prior as the training loss and the objective function in reconstruction to improve the image quality.Results: The proposed method showed an improved performance in preserving image details and reducing aliasing artifacts, compared with GRAPPA, ‐ESPRiT, model‐based deep learning architecture for inverse problems (MODL), and variational network (VN), last two were state‐of‐the‐art deep learning reconstruction methods. The proposed method generally achieved more than 3 dB peak signal‐to‐noise ratio improvement for compressed sensing and parallel imaging reconstructions compared with the other methods.Conclusions: The Bayesian estimation significantly improved the reconstruction performance, compared with the conventional ‐sparsity prior in compressed sensing reconstruction tasks. More importantly, the proposed reconstruction framework can be generalized for most MRI reconstruction scenarios.
16 September 2013 in IEEE Signal Processing Letters
In this letter, a new class of real-valued matrices is presented for deterministic compressed sensing. A base matrix is constructed by cyclic shifts of binary sequences in an optical orthogonal code (OOC). Then, a Hadamard matrix is used for its extension, which ultimately produces a real-valued matrix that takes the entries of 0, -1 and +1 before normalization. The new sensing matrix forms a tight frame with small coherence, which theoretically guarantees the average recovery performance of sparse signals with uniformly distributed supports. Several example sensing matrices are presented by employing a special type of OOCs obtained from modular Golomb rulers.
1 January 2026 in IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control