An exploratory study of explainable deep learning for predicting bone mineral density using clavicle features on chest radiographs: A multi‐task approach with regression and segmentation
The proposed multi-task learning model demonstrated the predictive rationale by focusing on the clavicle in chest radiographs, which is clinically relevant to BMD, and showed improved performance compared with the single-task model.
Authors
- Yukito Yoshida
- Yoshiyuki Iwao (ORCID: https://orcid.org/0009-0007-8713-1845)
- Ryoichi Nagata
- Michihiro Eto (ORCID: https://orcid.org/0009-0000-2159-2015)
- Takahiro Ochiai (ORCID: https://orcid.org/0009-0002-0881-0254)
- Kenshi Shiotsuki (ORCID: https://orcid.org/0009-0002-0337-2005)
- Yoshiki Asayama (ORCID: https://orcid.org/0000-0001-6495-4821)
- Tsuneo Kagawa
- Fumio Hashimoto (ORCID: https://orcid.org/0000-0003-2352-0538)
- Yuji Hatanaka (ORCID: https://orcid.org/0000-0002-8621-5592)
Institutions
- Chiba University (JP)
- Oita University (JP)
- Nippon Bunri University (JP)
- University of Florida (US)
- Oita University Hospital (JP)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2025-11-23
- DOI
- https://doi.org/10.1002/acm2.70336
- Citations
- 1
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 1.36