EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs

Koen D Oude Nijhuis, Britt Barvelink, Jasper Prijs, Yang Zhao, Zhibin Liao, Ruurd L Jaarsma, Frank F A IJpma, Joost W Colaris, Job N Doornberg, Mathieu M E Wijffels, Machine Learning Consortium

European Journal of Trauma and Emergency Surgery · 2025-12 · 51 (1)

DOI: 10.1007/s00068-024-02731-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Trauma and Emergency Surgery, online erschienen am 17.01.2025. Verfasst von Koen D Oude Nijhuis und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands. k.…. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Radiography, Radius Fractures, Wrist Injuries. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Distal radius fractures (DRFs) are often initially assessed by junior doctors under time constraints, with limited supervision, risking significant consequences if missed. Convolutional Neural Networks (CNNs) can aid in diagnosing fractures. This study aims to internally and externally validate an open source algorithm for the detection and localization of DRFs.

Methods

Patients from a level 1 trauma center from Adelaide, Australia that presented between 2016 and 2020 with wrist trauma were retrospectively included. Radiographs were reviewed confirming the presence or absence of a fracture, as well as annotating radius, ulna, and fracture location. An internal validation dataset from the same hospital was created. An external validation set was created with two other level 1 trauma centers, from Groningen and Rotterdam, the Netherlands. Three surgeons reviewed both sets for DRFs.

Results

The algorithm was trained on 659 radiographs. The internal validation set included 190 patients, showing an accuracy of 87% and an AUC of 0.93 for DRF detection. The external validation set consisted of 188 patients, with an accuracy and AUC were 82% and 0.88 respectively. Radial and ulnar bone segmentation on the internal validation was excellent with an AP50 of 99 and 98, but moderate for fracture segmentation with an AP50 of 29. For external validation the AP50 was 92, 89 and 25 for radius, ulna, and fracture respectively.

Conclusion

This open-source algorithm effectively detects DRFs with high accuracy and localizes them with moderate accuracy. It can assist clinicians in diagnosing suspected DRFs and is the first radiograph-based CNN externally validated on patients from multiple hospitals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Convolutional Neural NetworksRadiographyRadius FracturesWrist InjuriesAdultAgedAged, 80 and overFemaleHumansMaleMiddle AgedAlgorithmsRetrospective StudiesTrauma CentersWrist Fractures

Stichwörter der Autor:innen

Artificial intelligenceDistal radius fracturesTraumaWrist

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands. k.d.oude.nijhuis@umcg.nl.
  • Department of Trauma Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands. k.d.oude.nijhuis@umcg.nl.
  • Department of Orthopaedics and Sports Medicine, Erasmus University Medical Centre, Rotterdam, The Netherlands.
  • Department of Orthopaedic Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands.
  • Department of Trauma Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands.
  • Department of Orthopaedic Surgery, Flinders University and Medical Centre, Adelaide, South Australia, Australia.

Zitieren

APA

Oude Nijhuis, K. D., Barvelink, B., Prijs, J., Zhao, Y., Liao, Z., Jaarsma, R. L., IJpma, F. F. A., Colaris, J. W., Doornberg, J. N., Wijffels, M. M. E., & Machine Learning Consortium (2025). An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs. European Journal of Trauma and Emergency Surgery, 51(1). https://doi.org/10.1007/s00068-024-02731-4

Vancouver

Oude Nijhuis KD, Barvelink B, Prijs J, Zhao Y, Liao Z, Jaarsma RL, et al. An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs. European Journal of Trauma and Emergency Surgery. 2025;51(1). doi:10.1007/s00068-024-02731-4

BibTeX
@article{OudeNijhuis2025,
  author = {Oude Nijhuis, Koen D and Barvelink, Britt and Prijs, Jasper and Zhao, Yang and Liao, Zhibin and Jaarsma, Ruurd L and IJpma, Frank F A and Colaris, Joost W and Doornberg, Job N and Wijffels, Mathieu M E and Machine Learning Consortium, Machine Learning Consortium},
  title = {An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs},
  journal = {European Journal of Trauma and Emergency Surgery},
  year = {2025},
  volume = {51},
  number = {1},
  doi = {10.1007/s00068-024-02731-4}
}
Kostenlos starten →