Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918490871431168 |
|---|---|
| author | Sheombarsing, Ray van Riel, Max Heesterbeek, David Berg, Nico van den Sbrizzi, Alessandro |
| author_facet | Sheombarsing, Ray van Riel, Max Heesterbeek, David Berg, Nico van den Sbrizzi, Alessandro |
| contents | Conventional MRI reconstruction methods treat images and coil sensitivities as discrete objects, leading to high memory demands and limited structural awareness that hamper effective regularization. These limitations hinder accurate reconstruction in highly undersampled scenarios, such as dynamic 3D cardiac magnetic resonance (CMR). We introduce a discretization-free, memory-efficient, model-based framework for dynamic 2D and 3D MRI reconstruction from highly undersampled data. We represent magnetization and coil sensitivities as continuous objects -- differentiable functions -- using tensor products of univariate neural fields. This tensor product structure enables scalable optimization in high-dimensional spatiotemporal settings. Our method outperforms state-of-the-art model-based reconstructions in dynamic 2D and 3D MR settings, preserving structure and motion even under aggressive undersampling (e.g., acceleration factor 16). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08275 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions Sheombarsing, Ray van Riel, Max Heesterbeek, David Berg, Nico van den Sbrizzi, Alessandro Image and Video Processing Computer Vision and Pattern Recognition Conventional MRI reconstruction methods treat images and coil sensitivities as discrete objects, leading to high memory demands and limited structural awareness that hamper effective regularization. These limitations hinder accurate reconstruction in highly undersampled scenarios, such as dynamic 3D cardiac magnetic resonance (CMR). We introduce a discretization-free, memory-efficient, model-based framework for dynamic 2D and 3D MRI reconstruction from highly undersampled data. We represent magnetization and coil sensitivities as continuous objects -- differentiable functions -- using tensor products of univariate neural fields. This tensor product structure enables scalable optimization in high-dimensional spatiotemporal settings. Our method outperforms state-of-the-art model-based reconstructions in dynamic 2D and 3D MR settings, preserving structure and motion even under aggressive undersampling (e.g., acceleration factor 16). |
| title | Model-based Dynamic 3D MRI Reconstructions using Neural Fields and Tensor Product Expansions |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.08275 |