EUVIMEDEUVIMED entdecken
Open Access

Using deep learning for estimation of time-since-injury in pediatric accidental fractures

Farah W Brink, Brent Adler, Sven Bambach, Charmaine B Lo, Steven Rust, Christopher W Bartlett, Logan Bradshaw, M Katherine Henry, Diana Messer

Pediatric Radiology · 2025

DOI: 10.1007/s00247-025-06223-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Radiology, 2025. Verfasst von Farah W Brink und 8 weiteren Autor:innen. Beteiligte Einrichtung: Nationwide Children's Hospital, 700 Children's Drive, Columbus, OH, 43205, USA. farah.brink@nationwidechildrens.org. Hauptthemen laut MEDLINE: Deep Learning, Fractures, Bone, Image Processing, Computer-Assisted, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: AHRQ HHS, CDC HHS, Nationwide Children’s Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Estimating time-since-injury of healing fractures is imprecise, encompassing excessively wide timeframes. Most injured children are evaluated at non-children's hospitals, yet pediatric radiologists can disagree with up to one in six skeletal imaging interpretations from referring community hospitals. There is a need to improve image interpretation by considering additional methods for fracture dating. OBJECTIVE: To train and validate deep learning models to correctly estimate the age of pediatric accidental long bone fractures. MATERIALS AND METHODS: This secondary data analysis used radiographic images of accidental long bone fractures in children

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningFractures, BoneImage Processing, Computer-AssistedRadiographic Image Interpretation, Computer-AssistedAccidental InjuriesChildChild, PreschoolHumansInfantClavicleFeasibility StudiesRadiographySoftware ValidationTime Factors

Stichwörter der Autor:innen

Artificial intelligenceBoneChildrenDatingDeep learningFracturesRadiographs

Autor:innen und Institutionen

  • Nationwide Children's Hospital, 700 Children's Drive, Columbus, OH, 43205, USA. farah.brink@nationwidechildrens.org.
  • The Ohio State University Wexner Medical Center, Columbus, USA. farah.brink@nationwidechildrens.org.
  • Abigail Wexner Research Institute at Nationwide Children's Hospital, Columbus, USA.
  • Nationwide Children's Hospital, 700 Children's Drive, Columbus, OH, 43205, USA.
  • The Ohio State University Wexner Medical Center, Columbus, USA.
  • Clinical Futures, Division of General Pediatrics, and Department of Radiology, Children's Hospital of Philadelphia, Philadelphia, USA.

Förderung

  • AHRQ HHS
  • CDC HHS
  • Nationwide Children’s Hospital
  • Abigail Wexner Research Institute at Nationwide Children's Hospital
  • Agency for Healthcare Research and Quality
  • Centers for Disease Control and Prevention

Zitieren

APA

Brink, F. W., Adler, B., Bambach, S., Lo, C. B., Rust, S., Bartlett, C. W., Bradshaw, L., Henry, M. K., & Messer, D. (2025). Using deep learning for estimation of time-since-injury in pediatric accidental fractures. Pediatric Radiology. https://doi.org/10.1007/s00247-025-06223-4

Vancouver

Brink FW, Adler B, Bambach S, Lo CB, Rust S, Bartlett CW, et al. Using deep learning for estimation of time-since-injury in pediatric accidental fractures. Pediatric Radiology. 2025. doi:10.1007/s00247-025-06223-4

BibTeX
@article{Brink2025,
  author = {Brink, Farah W and Adler, Brent and Bambach, Sven and Lo, Charmaine B and Rust, Steven and Bartlett, Christopher W and Bradshaw, Logan and Henry, M Katherine and Messer, Diana},
  title = {Using deep learning for estimation of time-since-injury in pediatric accidental fractures},
  journal = {Pediatric Radiology},
  year = {2025},
  doi = {10.1007/s00247-025-06223-4}
}
Kostenlos starten →