Impact of Test Set Composition on AI Performance for Pediatric Radiograph Appendicular Skeleton Fracture Detection.

Saved in:
Bibliographic Details
Title: Impact of Test Set Composition on AI Performance for Pediatric Radiograph Appendicular Skeleton Fracture Detection.
Authors: Stranger N; Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria., Scherkl M; Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria., Stütz D; Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria., Janisch M; Division of Neuroradiology, Vascular and Interventional Radiology, Department of Radiology, Medical University of Graz, Auenbruggerplatz 9, Graz 8036, Austria., Singer G; Department of Pediatric and Adolescence Surgery, Medical University of Graz, Graz, Austria., Hankel S; Department of Pediatric and Adolescence Surgery, Medical University of Graz, Graz, Austria., Till H; Department of Pediatric and Adolescence Surgery, Medical University of Graz, Graz, Austria., Sackl M; Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria., Hržić F; Center for Artificial Intelligence and Cybersecurity, University of Rijeka, Rijeka, Croatia.; Department of Orthopaedic Surgery and Sports Medicine, Boston Children's Hospital, Harvard Medical School, Boston, Mass., Herzog S; Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria., Tschauner S; Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria.
Source: Radiology [Radiology] 2026 Feb; Vol. 318 (2), pp. e250540.
Publication Type: Journal Article
Journal Info: Publisher: Radiological Society of North America Country of Publication: United States NLM ID: 0401260 Publication Model: Print Cited Medium: Internet ISSN: 1527-1315 (Electronic) Linking ISSN: 00338419 NLM ISO Abbreviation: Radiology Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:1527-1315
DOI:10.1148/radiol.250540