Bayesian reconstruction of magnetic resonance images using Gaussian processes
Abstract A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based reconstruction. Here, we propose and demonst...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-39533-4 |
| _version_ | 1827875527189331968 |
|---|---|
| author | Yihong Xu Chad W. Farris Stephan W. Anderson Xin Zhang Keith A. Brown |
| author_facet | Yihong Xu Chad W. Farris Stephan W. Anderson Xin Zhang Keith A. Brown |
| author_sort | Yihong Xu |
| collection | DOAJ |
| description | Abstract A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based reconstruction. Here, we propose and demonstrate a Bayesian method to build statistical libraries of magnetic resonance (MR) images in k-space and use these libraries to identify optimal subsampling paths and reconstruction processes. Specifically, we compute a multivariate normal distribution based upon Gaussian processes using a publicly available library of T1-weighted images of healthy brains. We combine this library with physics-informed envelope functions to only retain meaningful correlations in k-space. This covariance function is then used to select a series of ring-shaped subsampling paths using Bayesian optimization such that they optimally explore space while remaining practically realizable in commercial MRI systems. Combining optimized subsampling paths found for a range of images, we compute a generalized sampling path that, when used for novel images, produces superlative structural similarity and error in comparison to previously reported reconstruction processes (i.e. 96.3% structural similarity and < 0.003 normalized mean squared error from sampling only 12.5% of the k-space data). Finally, we use this reconstruction process on pathological data without retraining to show that reconstructed images are clinically useful for stroke identification. Since the model trained on images of healthy brains could be directly used for predictions in pathological brains without retraining, it shows the inherent transferability of this approach and opens doors to its widespread use. |
| first_indexed | 2024-03-12T17:08:13Z |
| format | Article |
| id | doaj.art-5d3f77676e864a2f97a43f65e7d4e79b |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-12T17:08:13Z |
| publishDate | 2023-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5d3f77676e864a2f97a43f65e7d4e79b2023-08-06T11:14:05ZengNature PortfolioScientific Reports2045-23222023-08-0113111210.1038/s41598-023-39533-4Bayesian reconstruction of magnetic resonance images using Gaussian processesYihong Xu0Chad W. Farris1Stephan W. Anderson2Xin Zhang3Keith A. Brown4Department of Physics, Boston UniversityDepartment of Radiology, Boston Medical Center, Boston University Chobanian & Avedisian School of MedicineDepartment of Radiology, Boston Medical Center, Boston University Chobanian & Avedisian School of MedicineDepartment of Mechanical Engineering, Boston UniversityDepartment of Physics, Boston UniversityAbstract A central goal of modern magnetic resonance imaging (MRI) is to reduce the time required to produce high-quality images. Efforts have included hardware and software innovations such as parallel imaging, compressed sensing, and deep learning-based reconstruction. Here, we propose and demonstrate a Bayesian method to build statistical libraries of magnetic resonance (MR) images in k-space and use these libraries to identify optimal subsampling paths and reconstruction processes. Specifically, we compute a multivariate normal distribution based upon Gaussian processes using a publicly available library of T1-weighted images of healthy brains. We combine this library with physics-informed envelope functions to only retain meaningful correlations in k-space. This covariance function is then used to select a series of ring-shaped subsampling paths using Bayesian optimization such that they optimally explore space while remaining practically realizable in commercial MRI systems. Combining optimized subsampling paths found for a range of images, we compute a generalized sampling path that, when used for novel images, produces superlative structural similarity and error in comparison to previously reported reconstruction processes (i.e. 96.3% structural similarity and < 0.003 normalized mean squared error from sampling only 12.5% of the k-space data). Finally, we use this reconstruction process on pathological data without retraining to show that reconstructed images are clinically useful for stroke identification. Since the model trained on images of healthy brains could be directly used for predictions in pathological brains without retraining, it shows the inherent transferability of this approach and opens doors to its widespread use.https://doi.org/10.1038/s41598-023-39533-4 |
| spellingShingle | Yihong Xu Chad W. Farris Stephan W. Anderson Xin Zhang Keith A. Brown Bayesian reconstruction of magnetic resonance images using Gaussian processes Scientific Reports |
| title | Bayesian reconstruction of magnetic resonance images using Gaussian processes |
| title_full | Bayesian reconstruction of magnetic resonance images using Gaussian processes |
| title_fullStr | Bayesian reconstruction of magnetic resonance images using Gaussian processes |
| title_full_unstemmed | Bayesian reconstruction of magnetic resonance images using Gaussian processes |
| title_short | Bayesian reconstruction of magnetic resonance images using Gaussian processes |
| title_sort | bayesian reconstruction of magnetic resonance images using gaussian processes |
| url | https://doi.org/10.1038/s41598-023-39533-4 |
| work_keys_str_mv | AT yihongxu bayesianreconstructionofmagneticresonanceimagesusinggaussianprocesses AT chadwfarris bayesianreconstructionofmagneticresonanceimagesusinggaussianprocesses AT stephanwanderson bayesianreconstructionofmagneticresonanceimagesusinggaussianprocesses AT xinzhang bayesianreconstructionofmagneticresonanceimagesusinggaussianprocesses AT keithabrown bayesianreconstructionofmagneticresonanceimagesusinggaussianprocesses |