Comparison of image quality and lesion conspicuity between conventional and deep learning reconstruction in gadoxetic acid-enhanced liver MRI
DL reconstruction is feasible for 3D T1-weighted images across different spatial resolutions and phases. DL reconstruction showed superior image quality with reduced noise and ringing artifacts. Hepatic anatomic structures were more conspicuous on DL-reconstructed images.
Authors
- Jeong Hee Yoon (ORCID: https://orcid.org/0000-0002-9925-9973)
- Jae Hyun Kim
- Jeong Eun Lee
- Jeong Min Lee (ORCID: https://orcid.org/0000-0003-0561-8777)
- Jin Young Park (ORCID: https://orcid.org/0000-0003-2713-4490)
- So Hyun Park (ORCID: https://orcid.org/0000-0001-9935-2863)
Institutions
- Seoul National University Hospital (KR)
- Gachon University Gil Medical Center (KR)
- Inje University Busan Paik Hospital (KR)
- National University College (PR)
- Chungnam National University Hospital (KR)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2024-10-28
- DOI
- https://doi.org/10.1186/s13244-024-01825-2
- Citations
- 9
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 3.64
Funders
- Seoul National University
- Seoul National University Hospital
- GE Global Research
- College of Medicine, Seoul National University