Self‐Supervised Joint Reconstruction and Denoising of <scp>T2</scp> ‐Weighted <scp>PROPELLER MRI</scp> of the Lung at <scp>0.55T</scp>
By leveraging the intrinsic data redundancy in PROPELLER sampling and extending the Noise2Noise concept, the proposed self-supervised framework enabled simultaneous reconstruction and denoising of lung images at 0.55T to address the low-SNR challenge at low-field. It holds great potential for broad use in other low-field MRI applications.
Authors
- Qiuting Wen (ORCID: https://orcid.org/0000-0002-7885-4036)
- Christoph Maier (ORCID: https://orcid.org/0000-0001-7354-4795)
- Jingjia Chen (ORCID: https://orcid.org/0000-0002-6023-1033)
- Haoyang Pei (ORCID: https://orcid.org/0009-0007-9258-673X)
- Steven S. Shin (ORCID: https://orcid.org/0000-0003-4353-307X)
- Mary T. Bruno (ORCID: https://orcid.org/0000-0003-1625-0293)
- Hersh Chandarana (ORCID: https://orcid.org/0000-0002-6807-4589)
- Li Feng (ORCID: https://orcid.org/0000-0002-8692-7645)
- William H. Moore (ORCID: https://orcid.org/0009-0008-5860-3804)
Institutions
- Indiana University School of Medicine
- Indiana University – Purdue University Indianapolis (US)
- New York University (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-12-12
- DOI
- https://doi.org/10.1002/mrm.70224
- Primary Topic
- Atomic and Subatomic Physics Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00