Enhancing vertebral fracture prediction using multitask deep learning computed tomography imaging of bone and muscle
Question Vertebral fracture risk remains underestimated in many individuals undergoing CT scans for other reasons, highlighting the need for improved opportunistic prediction tools. Findings A multitask deep learning model integrating both bone and muscle features from CT scans demonstrated superior performance compared to bone-only and traditional clinical models, including FRAX. Clinical relevance The proposed model enables accurate vertebral fracture risk prediction using routinely acquired CT scans, facilitating early identification and intervention without the need for additional tests.
Authors
- Seung Shin Park (ORCID: https://orcid.org/0000-0001-5719-1539)
- Sung Hye Kong (ORCID: https://orcid.org/0000-0002-8791-0909)
- Sung Bae Park (ORCID: https://orcid.org/0000-0002-4652-3056)
- Sang Wan Kim (ORCID: https://orcid.org/0000-0001-9561-9110)
- Jaegul Choo (ORCID: https://orcid.org/0000-0003-1071-4835)
- Chan Soo Shin (ORCID: https://orcid.org/0000-0002-5829-4465)
- Jung Hee Kim (ORCID: https://orcid.org/0000-0003-1932-0234)
- Saemee Choi
- Wonwoo Cho (ORCID: https://orcid.org/0000-0003-4547-734X)
Institutions
- Seoul National University (KR)
- Korea Advanced Institute of Science and Technology (KR)
- Seoul National University Hospital (KR)
- Seoul National University Bundang Hospital (KR)
- Korea Pharma (South Korea) (KR)
- SNUH SMG-SNU Boramae Medical Center (KR)
- National University College (PR)
Publication Details
- Journal
- European Radiology
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1007/s00330-025-12049-3
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00