Deep learning reconstruction for fast cardiovascular magnetic resonance imaging protocol: A comparative study with conventional cardiovascular magnetic resonance
DL reconstruction of CMR sequences reduced acquisition times by 57%(159.2/277.1) and enhanced image quality compared to conventional SENSE reconstruction, while maintaining consistent quantitative parameters and diagnostic accuracy across all sequences. These results advocate integrating DL-accelerated workflows into clinical practice.
Authors
- Xiuzheng Yue
- Nan Zhang (ORCID: https://orcid.org/0000-0002-9960-6859)
- Mengmeng Yu
- Yinyin Chen (ORCID: https://orcid.org/0000-0002-1192-671X)
- Hua Yin (ORCID: https://orcid.org/0000-0002-0071-9037)
- Hang Jin (ORCID: https://orcid.org/0000-0002-6810-2527)
- Hongfei Lü (ORCID: https://orcid.org/0000-0001-9732-0833)
- Fan Du (ORCID: https://orcid.org/0000-0002-4383-8888)
- Shiya Wang (ORCID: https://orcid.org/0009-0005-0399-1254)
- Mengsu Zeng (ORCID: https://orcid.org/0000-0001-6054-0824)
Institutions
- Shanghai Medical College of Fudan University (CN)
- Fudan University (CN)
- Philips (China) (CN)
- Zhongshan Hospital (CN)
Publication Details
- Journal
- Journal of Cardiovascular Magnetic Resonance
- Published
- 2025-11-28
- DOI
- https://doi.org/10.1016/j.jocmr.2025.102017
- Citations
- 1
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.36