NeuroMix-DL: Improving imaging quality of a fast multiparametric MRI protocol using deep learning
The SwinUNETR model offers a viable approach for improving the quality of fast multi-contrast MR images while effectively mitigating artifacts, improving the cost-benefit ratio of MRI.
Authors
- Moss Zhao (ORCID: https://orcid.org/0000-0002-0210-7739)
- Tim Sprenger (ORCID: https://orcid.org/0000-0001-7037-8605)
- Stefan Skare (ORCID: https://orcid.org/0000-0001-5403-2153)
- H. Zaidi
- Johannes H. Decker (ORCID: https://orcid.org/0000-0002-4143-2673)
- Amirhossein Sanaat (ORCID: https://orcid.org/0000-0001-8437-2060)
- Michael Moseley
- Greg Zaharchuk
- Ramy Hussein
Institutions
- University of Geneva (CH)
- University Medical Center Groningen (NL)
- Karolinska University Hospital (SE)
- University Hospital of Geneva (CH)
- Stanford University (US)
Publication Details
- Journal
- European Journal of Radiology
- Published
- 2026-03-11
- DOI
- https://doi.org/10.1016/j.ejrad.2026.112795
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00