Deep learning enhances reliability of dynamic contrast-enhanced MRI in diffuse gliomas: bypassing post-processing and providing uncertainty maps
Question Can a deep learning model enhance the reliability of dynamic contrast-enhanced MRI (DCE-MRI) for more consistent and clinically acceptable glioma imaging? Findings A spatiotemporal deep learning model outperformed the Tofts model in Ktrans reliability and preserved diagnostic performance for IDH mutation and glioma grade, bypassing arterial input function estimation. Clinical relevance Enhancing DCE-MRI reliability with deep learning improves imaging consistency, supports molecular tumor characterization through reproducible pharmacokinetic maps, and enables personalized treatment planning, which might lead to better clinical outcomes for patients with diffuse gliomas.
Authors
- Kyu Sung Choi (ORCID: https://orcid.org/0000-0002-5175-3307)
- Jin Wook Chung (ORCID: https://orcid.org/0000-0002-1090-6872)
- H. Lee (ORCID: https://orcid.org/0000-0002-1138-3700)
- Inpyeong Hwang (ORCID: https://orcid.org/0000-0002-1291-8973)
- Junhyeok Lee (ORCID: https://orcid.org/0000-0001-7489-5829)
- Jaejun Yoo (ORCID: https://orcid.org/0000-0001-5252-9668)
- Jung‐Hyun Park (ORCID: https://orcid.org/0000-0002-9547-9055)
- Seung Hong Choi
- Young Wook Lyoo
Institutions
- Seoul National University (KR)
- Seoul Metropolitan Government (KR)
- Seoul National University Hospital (KR)
- SNUH SMG-SNU Boramae Medical Center (KR)
- National University College (PR)
- Ulsan National Institute of Science and Technology (KR)
Publication Details
- Journal
- European Radiology
- Published
- 2025-04-19
- DOI
- https://doi.org/10.1007/s00330-025-11588-z
- Citations
- 2
- Primary Topic
- MRI in cancer diagnosis
- Type
- article
- Field-Weighted Citation Impact
- 2.72
Funders
- National Research Foundation
- Seoul National University
- Korea Health Industry Development Institute
- National Research Foundation of Korea
- Seoul National University Hospital
- Ministry of Science and ICT, South Korea