Development and validation of deep learning models for identifying the brand of pedicle screws on plain spine radiographs
The DL models demonstrated stable performance in identifying the brand of PS-based instrumentation based on AP and/or lateral images of PRS, which may assist orthopedic spine surgeons in preoperative revision planning in clinical practice.
Authors
- Wei Hsiung (ORCID: https://orcid.org/0000-0002-7705-159X)
- Shih‐Tien Wang (ORCID: https://orcid.org/0000-0002-0942-8332)
- Hsi‐Hsien Lin (ORCID: https://orcid.org/0000-0003-2798-3855)
- Yu‐Cheng Yao (ORCID: https://orcid.org/0000-0001-7555-4321)
- Po‐Hsin Chou (ORCID: https://orcid.org/0000-0001-5899-1124)
- Hung‐Hsun Chen (ORCID: https://orcid.org/0000-0001-6437-9804)
- Yu‐Hsuan Tang
- Cheng‐Li Lin (ORCID: https://orcid.org/0000-0002-7315-7709)
- Ying‐Chou Sun
Institutions
- Fu Jen Catholic University (TW)
- National Yang Ming Chiao Tung University (TW)
- Yuanpei University (TW)
- Taipei Veterans General Hospital (TW)
- Ministry of Health and Welfare (TW)
- National Cheng Kung University Hospital (TW)
Publication Details
- Journal
- JOR Spine
- Published
- 2024-09-01
- DOI
- https://doi.org/10.1002/jsp2.70001
- Citations
- 3
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.55