Accelerating 3D radial MPnRAGE using a self‐supervised deep factor model
The proposed DFM offers a superior representation of the multicontrast images compared to subspace models, especially in the highly accelerated MPnRAGE setting. The self-supervised training is ideal for methods with both high resolution and a large parametric dimension, where training neural networks can become computationally demanding without a dedicated high-end GPU array.
Authors
- Steven Kecskemeti (ORCID: https://orcid.org/0000-0003-3589-430X)
- Nima Yaghoobi
- James H. Holmes (ORCID: https://orcid.org/0000-0002-0936-3700)
- Mathews Jacob (ORCID: https://orcid.org/0000-0001-6196-3933)
- Vincent A. Magnotta (ORCID: https://orcid.org/0000-0001-8639-5354)
- Curtis A. Corum (ORCID: https://orcid.org/0000-0002-4994-6206)
- Yan Chen (ORCID: https://orcid.org/0009-0003-6886-1886)
Institutions
- University of Iowa (US)
- University of Wisconsin–Madison (US)
- TSI (United States) (US)
- University of Virginia (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-06-02
- DOI
- https://doi.org/10.1002/mrm.30549
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health
- GE Healthcare
- Eunice Kennedy Shriver National Institute of Child Health and Human Development