An approximate message passing algorithm for rapid parameter-free compressed sensing MRI
For certain sensing matrices, the Approximate Message Passing (AMP) algorithm efficiently reconstructs undersampled signals. However, in Magnetic Resonance Imaging (MRI), where Fourier coefficients of a natural image are sampled with variable density, AMP encounters convergence problems. In response...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2020
|
| _version_ | 1826308910854701056 |
|---|---|
| author | Millard, C Hess, AT Mailhe, B Tanner, J |
| author_facet | Millard, C Hess, AT Mailhe, B Tanner, J |
| author_sort | Millard, C |
| collection | OXFORD |
| description | For certain sensing matrices, the Approximate Message Passing (AMP) algorithm efficiently reconstructs undersampled signals. However, in Magnetic Resonance Imaging (MRI), where Fourier coefficients of a natural image are sampled with variable density, AMP encounters convergence problems. In response we present an algorithm based on Orthogonal AMP constructed specifically for variable density partial Fourier sensing matrices. For the first time in this setting a state evolution has been observed. A practical advantage of state evolution is that Stein's Unbiased Risk Estimate (SURE) can be effectively implemented, yielding an algorithm with no free parameters. We empirically evaluate the effectiveness of the parameter-free algorithm on simulated data and find that it converges over 5x faster and to a lower mean-squared error solution than Fast Iterative Shrinkage-Thresholding (FISTA). |
| first_indexed | 2024-03-07T07:26:15Z |
| format | Conference item |
| id | oxford-uuid:d2d27e57-db47-4544-a9f0-e07332e95c8e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:26:15Z |
| publishDate | 2020 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:d2d27e57-db47-4544-a9f0-e07332e95c8e2022-11-15T14:25:43ZAn approximate message passing algorithm for rapid parameter-free compressed sensing MRIConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d2d27e57-db47-4544-a9f0-e07332e95c8eEnglishSymplectic ElementsIEEE2020Millard, CHess, ATMailhe, BTanner, JFor certain sensing matrices, the Approximate Message Passing (AMP) algorithm efficiently reconstructs undersampled signals. However, in Magnetic Resonance Imaging (MRI), where Fourier coefficients of a natural image are sampled with variable density, AMP encounters convergence problems. In response we present an algorithm based on Orthogonal AMP constructed specifically for variable density partial Fourier sensing matrices. For the first time in this setting a state evolution has been observed. A practical advantage of state evolution is that Stein's Unbiased Risk Estimate (SURE) can be effectively implemented, yielding an algorithm with no free parameters. We empirically evaluate the effectiveness of the parameter-free algorithm on simulated data and find that it converges over 5x faster and to a lower mean-squared error solution than Fast Iterative Shrinkage-Thresholding (FISTA). |
| spellingShingle | Millard, C Hess, AT Mailhe, B Tanner, J An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title | An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title_full | An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title_fullStr | An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title_full_unstemmed | An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title_short | An approximate message passing algorithm for rapid parameter-free compressed sensing MRI |
| title_sort | approximate message passing algorithm for rapid parameter free compressed sensing mri |
| work_keys_str_mv | AT millardc anapproximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT hessat anapproximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT mailheb anapproximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT tannerj anapproximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT millardc approximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT hessat approximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT mailheb approximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri AT tannerj approximatemessagepassingalgorithmforrapidparameterfreecompressedsensingmri |