Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms--are they on par with humans for diagnosing fractures?

Background and purpose -- Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this stu...

Descripción completa

Detalles Bibliográficos
Publicado en:Acta Orthopaedica Vol. 88; no. 6; pp. 581 - 587
Autores principales: Olczak, Jakub, Fahlberg, Niklas, Maki, Atsuto, Razavian, Ali Sharif, Jilert, Anthony, Stark, André, Sköldenberg, Olof, Gordon, Max
Formato: diagnostic images research tables/charts Journal Article
Publicado: Medical Journals Sweden AB Dec2017
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=126129120&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 126129120
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        17453674
        1BVL
      jtl: Acta Orthopaedica
      issn: 17453674
      maglogo: N
    pubinfo:
      dt: Dec2017
      vid: 88
      iid: 6
      pid: 59195
      pub: Medical Journals Sweden AB
    artinfo:
      ui:
        126129120
        126129120
        126129120
        10.1080/17453674.2017.1344459
        126129120
      ppf: 581
      ppct: 6
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms--are they on par with humans for diagnosing fractures?
      aug:
        au:
          Olczak, Jakub
          Fahlberg, Niklas
          Maki, Atsuto
          Razavian, Ali Sharif
          Jilert, Anthony
          Stark, André
          Sköldenberg, Olof
          Gordon, Max
        affil: Department of Clinical Sciences, Karolinska Institutet, DanderydHospital
      sug:
        subj:
          Artificial Intelligence
          Fractures Diagnosis
          Bone and Bones Radiography
          Image Interpretation, Computer Assisted
          Human
          Hospitals
          Neural Networks (Computer)
          kappa Statistic
          Validity
          Wrist Radiography
          Hand Radiography
          Ankle Radiography
          Dominance, Cerebral
          Orthopedic Surgery
          Surgeons
          Algorithms
      ab: Background and purpose -- Recent advances in artificial intelligence (deep learning) have shown remarkable performance in classifying non-medical images, and the technology is believed to be the next technological revolution. So far it has never been applied in an orthopedic setting, and in this study we sought to determine the feasibility of using deep learning for skeletal radiographs. Methods -- We extracted 256,000 wrist, hand, and ankle radiographs from Danderyd's Hospital and identified 4 classes: fracture, laterality, body part, and exam view. We then selected 5 openly available deep learning networks that were adapted for these images. The most accurate network was benchmarked against a gold standard for fractures. We furthermore compared the network's performance with 2 senior orthopedic surgeons who reviewed images at the same resolution as the network. Results -- All networks exhibited an accuracy of at least 90% when identifying laterality, body part, and exam view. The final accuracy for fractures was estimated at 83% for the best performing network. The network performed similarly to senior orthopedic surgeons when presented with images at the same resolution as the network. The 2 reviewer Cohen's kappa under these conditions was 0.76. Interpretation -- This study supports the use for orthopedic radiographs of artificial intelligence, which can perform at a human level. While current implementation lacks important features that surgeons require, e.g. risk of dislocation, classifications, measurements, and combining multiple exam views, these problems have technical solutions that are waiting to be implemented for orthopedics.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N