Open-source convolutional neural network to classify distal radial fractures according to the AO/OTA classification on plain radiographs.

Purpose: Convolutional Neural Networks (CNNs) have shown promise in fracture detection, but their ability to improve surgeons' inconsistent fracture classification remains unstudied. Therefore, our aim was create and (externally) validate the performance of an open-source CNN algorithm to classify D...

Full description

Bibliographic Details
Published in:European Journal of Trauma & Emergency Surgery Vol. 51; no. 1; pp. 1 - 11
Main Authors: Oude Nijhuis, Koen D., Prijs, Jasper, Barvelink, Britt, van Luit, Hans, Zhao, Yang, Liao, Zhibin, Jaarsma, Ruurd L., IJpma, Frank F. A., Wijffels, Mathieu M. E., Doornberg, Job N., Colaris, Joost W., Laane, Charlotte, Canta, Olga, Hoeksema, Sanne, Aksakal, Kaan, Mhmud, Haras, Jutte, Paul, Mallee, Wouter, Duckworth, Andrew, Schep, Niels
Format: diagnostic images research tables/charts Journal Article
Published: Springer Nature 7/21/2025
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=186782146&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 186782146
    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: 7/21/2025
      vid: 51
      iid: 1
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        186782146
        186782146
        186782146
        10.1007/s00068-025-02931-6
        186782146
      ppf: 1
      ppct: 10
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Open-source convolutional neural network to classify distal radial fractures according to the AO/OTA classification on plain radiographs.
      aug:
        au:
          Oude Nijhuis, Koen D.
          Prijs, Jasper
          Barvelink, Britt
          van Luit, Hans
          Zhao, Yang
          Liao, Zhibin
          Jaarsma, Ruurd L.
          IJpma, Frank F. A.
          Wijffels, Mathieu M. E.
          Doornberg, Job N.
          Colaris, Joost W.
          Laane, Charlotte
          Canta, Olga
          Hoeksema, Sanne
          Aksakal, Kaan
          Mhmud, Haras
          Jutte, Paul
          Mallee, Wouter
          Duckworth, Andrew
          Schep, Niels
        affil: https://ror.org/03cv38k47 Department of Orthopedic Surgery, University Medical Centre Groningen and Groningen University, Groningen, The Netherlands
      sug:
        subj:
          Radius Fractures, Distal Classification
          Radius Fractures, Distal Radiography
          Radiography Methods
          Convolutional Neural Networks Evaluation
          Classification Algorithms Evaluation
          Validity
          Severity of Injury
          Human
          Validation Studies
          Radius Fractures, Distal Pathology
          Machine Learning Algorithms
          Trauma Centers
          Surgeons
          ROC Curve
          Descriptive Statistics
          Interrater Reliability
          Intrarater Reliability
          Wrist Fractures
          Radius Fractures, Distal Diagnosis
          Predictive Value of Tests
          Sensitivity and Specificity
      ab: Purpose: Convolutional Neural Networks (CNNs) have shown promise in fracture detection, but their ability to improve surgeons' inconsistent fracture classification remains unstudied. Therefore, our aim was create and (externally) validate the performance of an open-source CNN algorithm to classify DRFs according to the AO/OTA classification system? Methods: Patients with postero-anterior, lateral and oblique radiographs were included. Radiographs were classified according to the AO/OTA-classification and were used to train a CNN algorithm. The algorithm was tested on an internal and external validation set (two other level 1 trauma centers), with the DRFs classified by three independent surgeons. Results: 659 radiographs were used to train the algorithm. Internal- and external validation sets contained 190 and 188 patients, respectively. Upon internal validation, the CNN had an accuracy of 62% and an area under receiving operating characteristic curve (AUC) of 0.63–0.93 (type 2R3A 0.84, type 2R3B 0.63, type 2R3C 0.75, and no DRF 0.93). On the external validation, the algorithm has an accuracy of 61% and an AUC of 0.56–0.88 (type 2R3A 0.82, type 2R3B 0.56, type 2R3C 0.75, and no DRF 0.88). Conclusion: The presented algorithm has demonstrated excellent accuracy in classifying type 2R3A DRFs and excluding DRFs. However, poor to moderate accuracy is observed in classifying 2R3B and 2R3C DRFs according to the AO/OTA system, similar to limited surgeons' inter-observer agreement. These results show that despite previous excellence in fracture detection, CNN-algorithms struggle with classifying; potentially showing the inherent problems with these classification systems.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N