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

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 vali...

Descripción completa

Detalles Bibliográficos
Publicado en:European Journal of Trauma & Emergency Surgery Vol. 51; no. 1; pp. 1 - 9
Autores principales: Oude Nijhuis, Koen D., Barvelink, Britt, Prijs, Jasper, Zhao, Yang, Liao, Zhibin, Jaarsma, Ruurd L., IJpma, Frank F. A., Colaris, Joost W., Doornberg, Job N., Wijffels, Mathieu M. E., On behalf of the Machine Learning Consortium, van Luit, Hans, Canta, Olga, Hoeksema, Sanne, Laane, Charlotte L.E., Aksakal, Kaan, Mhmud, Haras, Jutte, Paul, Gordon, Max, Mallee, Wouter
Formato: Journal Article
Publicado: Springer Nature 2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=182633001&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 182633001
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        18639933
        3C05
      jtl: European Journal of Trauma & Emergency Surgery
      issn: 18639933
      maglogo: N
    pubinfo:
      dt: 2025
      vid: 51
      iid: 1
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        182633001
        10.1007/s00068-024-02731-4
        182633001
      ppf: 1
      ppct: 8
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs.
      aug:
        au:
          Oude Nijhuis, Koen D.
          Barvelink, Britt
          Prijs, Jasper
          Zhao, Yang
          Liao, Zhibin
          Jaarsma, Ruurd L.
          IJpma, Frank F. A.
          Colaris, Joost W.
          Doornberg, Job N.
          Wijffels, Mathieu M. E.
          On behalf of the Machine Learning Consortium
          van Luit, Hans
          Canta, Olga
          Hoeksema, Sanne
          Laane, Charlotte L.E.
          Aksakal, Kaan
          Mhmud, Haras
          Jutte, Paul
          Gordon, Max
          Mallee, Wouter
        affil: https://ror.org/03cv38k47 Department of Orthopaedic Surgery, University Medical Centre Groningen and Groningen University, Hanzeplein 1, 9713PZ, Groningen, the Netherlands
      sug:
      ab: 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.
      pubtype: Academic Journal
      doctype: Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N