Low-Rank Conjugate Gradient-Net for Accelerated Cardiac MR Imaging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915024393469952 |
|---|---|
| author | Patel, Jaykumar H. Kadota, Brenden T. Sheagren, Calder D. Chiew, Mark Wright, Graham A. |
| author_facet | Patel, Jaykumar H. Kadota, Brenden T. Sheagren, Calder D. Chiew, Mark Wright, Graham A. |
| contents | Cardiovascular diseases (CVDs) remain the leading cause of mortality and morbidity worldwide. Both diagnosis and prognosis of these diseases benefit from high-quality imaging, which cardiac magnetic resonance imaging provides. CMR imaging requires lengthy acquisition times and multiple breath-holds for a complete exam, which can lead to patient discomfort and frequently results in image artifacts. In this work, we present a Low-rank tensor U-Net method (LowRank-CGNet) that rapidly reconstructs highly undersampled data with a variety of anatomy, contrast, and undersampling artifacts. The model uses conjugate gradient data consistency to solve for the spatial and temporal bases and employs a U-Net to further regularize the basis vectors. Currently, model performance is superior to a standard U-Net, but inferior to conventional compressed sensing methods. In the future, we aim to further improve model performance by increasing the U-Net size, extending the training duration, and dynamically updating the tensor rank for different anatomies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_11175 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Low-Rank Conjugate Gradient-Net for Accelerated Cardiac MR Imaging Patel, Jaykumar H. Kadota, Brenden T. Sheagren, Calder D. Chiew, Mark Wright, Graham A. Image and Video Processing Signal Processing Cardiovascular diseases (CVDs) remain the leading cause of mortality and morbidity worldwide. Both diagnosis and prognosis of these diseases benefit from high-quality imaging, which cardiac magnetic resonance imaging provides. CMR imaging requires lengthy acquisition times and multiple breath-holds for a complete exam, which can lead to patient discomfort and frequently results in image artifacts. In this work, we present a Low-rank tensor U-Net method (LowRank-CGNet) that rapidly reconstructs highly undersampled data with a variety of anatomy, contrast, and undersampling artifacts. The model uses conjugate gradient data consistency to solve for the spatial and temporal bases and employs a U-Net to further regularize the basis vectors. Currently, model performance is superior to a standard U-Net, but inferior to conventional compressed sensing methods. In the future, we aim to further improve model performance by increasing the U-Net size, extending the training duration, and dynamically updating the tensor rank for different anatomies. |
| title | Low-Rank Conjugate Gradient-Net for Accelerated Cardiac MR Imaging |
| topic | Image and Video Processing Signal Processing |
| url | https://arxiv.org/abs/2411.11175 |