StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913616888856576 |
|---|---|
| author | Mayo, Perla Cencini, Matteo Pirkl, Carolin M. Menzel, Marion I. Tosetti, Michela Menze, Bjoern H. Golbabaee, Mohammad |
| author_facet | Mayo, Perla Cencini, Matteo Pirkl, Carolin M. Menzel, Marion I. Tosetti, Michela Menze, Bjoern H. Golbabaee, Mohammad |
| contents | Magnetic Resonance Fingerprinting (MRF) is a time-efficient approach to quantitative MRI for multiparametric tissue mapping. The reconstruction of quantitative maps requires tailored algorithms for removing aliasing artefacts from the compressed sampled MRF acquisitions. Within approaches found in the literature, many focus solely on two-dimensional (2D) image reconstruction, neglecting the extension to volumetric (3D) scans despite their higher relevance and clinical value. A reason for this is that transitioning to 3D imaging without appropriate mitigations presents significant challenges, including increased computational cost and storage requirements, and the need for large amount of ground-truth (artefact-free) data for training. To address these issues, we introduce StoDIP, a new algorithm that extends the ground-truth-free Deep Image Prior (DIP) reconstruction to 3D MRF imaging. StoDIP employs memory-efficient stochastic updates across the multicoil MRF data, a carefully selected neural network architecture, as well as faster nonuniform FFT (NUFFT) transformations. This enables a faster convergence compared against a conventional DIP implementation without these features. Tested on a dataset of whole-brain scans from healthy volunteers, StoDIP demonstrated superior performance over the ground-truth-free reconstruction baselines, both quantitatively and qualitatively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02367 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations Mayo, Perla Cencini, Matteo Pirkl, Carolin M. Menzel, Marion I. Tosetti, Michela Menze, Bjoern H. Golbabaee, Mohammad Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Magnetic Resonance Fingerprinting (MRF) is a time-efficient approach to quantitative MRI for multiparametric tissue mapping. The reconstruction of quantitative maps requires tailored algorithms for removing aliasing artefacts from the compressed sampled MRF acquisitions. Within approaches found in the literature, many focus solely on two-dimensional (2D) image reconstruction, neglecting the extension to volumetric (3D) scans despite their higher relevance and clinical value. A reason for this is that transitioning to 3D imaging without appropriate mitigations presents significant challenges, including increased computational cost and storage requirements, and the need for large amount of ground-truth (artefact-free) data for training. To address these issues, we introduce StoDIP, a new algorithm that extends the ground-truth-free Deep Image Prior (DIP) reconstruction to 3D MRF imaging. StoDIP employs memory-efficient stochastic updates across the multicoil MRF data, a carefully selected neural network architecture, as well as faster nonuniform FFT (NUFFT) transformations. This enables a faster convergence compared against a conventional DIP implementation without these features. Tested on a dataset of whole-brain scans from healthy volunteers, StoDIP demonstrated superior performance over the ground-truth-free reconstruction baselines, both quantitatively and qualitatively. |
| title | StoDIP: Efficient 3D MRF image reconstruction with deep image priors and stochastic iterations |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2408.02367 |