Deep Learning Reconstruction Combined With Conventional Acceleration Improves Image Quality of 3 T Brain MRI and Does Not Impact Quantitative Diffusion Metrics
In this comparative study, we found that the combination of conventional acceleration and DRB reconstruction improves image quality and enables faster acquisition of ssEPI DWI. Nevertheless, a tradeoff between increased acceleration with risk of stronger artifacts and high-resolution with longer acquisition time needs to be considered, especially for application in cerebral MRI.
Authors
- Jakob Weiß
- Horst Urbach (ORCID: https://orcid.org/0000-0001-7264-4807)
- Fabian Bamberg (ORCID: https://orcid.org/0000-0002-7460-3942)
- Caroline Wilpert (ORCID: https://orcid.org/0000-0003-2375-2478)
- Maxim Zaitsev (ORCID: https://orcid.org/0000-0001-7530-1228)
- C. Voß (ORCID: https://orcid.org/0000-0002-9952-9072)
- Ralph Strecker (ORCID: https://orcid.org/0000-0002-8232-8952)
- Maximilian Frederik Russe (ORCID: https://orcid.org/0000-0003-3187-2429)
- Marco Reisert (ORCID: https://orcid.org/0000-0003-2742-1940)
- Roberta Bedin (ORCID: https://orcid.org/0000-0001-5006-3294)
- Alexander Rau (ORCID: https://orcid.org/0000-0001-5881-6043)
- Stephan Rau
Institutions
- University Medical Center Freiburg (DE)
- Siemens Healthineers (Germany) (DE)
Publication Details
- Journal
- Investigative Radiology
- Published
- 2025-02-07
- DOI
- https://doi.org/10.1097/rli.0000000000001158
- Citations
- 4
- Primary Topic
- Advanced Neuroimaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 5.44