Optimized reconstruction of undersampled Dixon sequences using new memory‐efficient unrolled deep neural networks: <scp>HalfVarNet</scp> and <scp>HalfDIRCN</scp>
The proposed method enables time and memory-efficient reconstruction of undersampled 3D MRI data, supporting its potential for clinical application.
Authors
- Marc Dubois (ORCID: https://orcid.org/0000-0002-9195-7363)
- Amira Trabelsi (ORCID: https://orcid.org/0000-0002-4622-3766)
- David Bendahan (ORCID: https://orcid.org/0000-0002-1502-0958)
- Sandra Martin (ORCID: https://orcid.org/0009-0000-8612-612X)
- Redha Abdeddaïm (ORCID: https://orcid.org/0000-0001-6126-1106)
- Maxime Guye (ORCID: https://orcid.org/0000-0002-4435-2257)
- Rémi André (ORCID: https://orcid.org/0000-0003-0476-1037)
Institutions
- Centre National de la Recherche Scientifique (FR)
- Aix-Marseille Université (FR)
- Multi-Phase Technologies (United States) (US)
- Institut Fresnel (FR)
- Centre de Résonance Magnétique Biologique et Médicale (FR)
- Centrale Méditerranée (FR)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-09-08
- DOI
- https://doi.org/10.1002/mrm.70070
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00