Self‐Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning
Rep2Rep learning offers an effective self-supervised denoising for low-field MRI by leveraging routinely acquired multi-repetition data. Its noise-adaptivity enables generalization to different SNR regimes without clean reference images. This makes Rep2Rep learning a promising tool for improving image quality and scan efficiency in low-field MRI.
Authors
- Yao Wang (ORCID: https://orcid.org/0009-0007-4912-808X)
- Luke Ginocchio (ORCID: https://orcid.org/0000-0002-0183-7246)
- Jingjia Chen (ORCID: https://orcid.org/0000-0002-6023-1033)
- Nikola Janjušević (ORCID: https://orcid.org/0000-0002-8277-3175)
- Mary T. Bruno (ORCID: https://orcid.org/0000-0003-1625-0293)
- Hersh Chandarana (ORCID: https://orcid.org/0000-0002-6807-4589)
- Feng Li (ORCID: https://orcid.org/0000-0001-9945-6208)
- Yuhui Huang (ORCID: https://orcid.org/0000-0002-3270-8332)
Institutions
- New York University (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-11-09
- DOI
- https://doi.org/10.1002/mrm.70155
- Primary Topic
- Image and Signal Denoising Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Center for Advanced Imaging Innovation and Research
- Centre d'Imagerie BioMédicale
- National Institutes of Health
- National Institute of Biomedical Imaging and Bioengineering