Automated AI fracture detection in initial presentation pediatric wrist X-rays: effects and benefits of adding follow-up examinations
Adding follow-up X-rays did not enhance classification performance but improved fracture localization in object detection tasks. These findings suggest that including follow-up data shows no relevant improvement in the detection rate of fractures but can enhance AI applications for pediatric wrist fracture detection, particularly for object detection models.
Authors
- Mario Scherkl
- Holger Till (ORCID: https://orcid.org/0000-0002-1350-596X)
- Georg Singer (ORCID: https://orcid.org/0000-0003-4770-3144)
- Nikolaus Stranger (ORCID: https://orcid.org/0009-0001-7274-9403)
- Andreea Ciornei-Hoffman (ORCID: https://orcid.org/0009-0003-1235-691X)
- Franko Hržić (ORCID: https://orcid.org/0000-0003-1513-0337)
- Sebastian Tschauner (ORCID: https://orcid.org/0000-0002-7873-9839)
- Tristan Till
Institutions
- Boston Children's Hospital (US)
- University of Rijeka (HR)
- Medical University of Graz (AT)
- Klinički Bolnički Centar Rijeka (HR)
Publication Details
- Journal
- La radiologia medica
- Published
- 2025-11-13
- DOI
- https://doi.org/10.1007/s11547-025-02153-1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00