Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference.

Objective: To clinically validate a fully automated deep convolutional neural network (DCNN) for detection of surgically proven meniscus tears.Materials and Methods: One hundred consecutive patients were retrospectively included, who underwent knee MRI and knee arthroscopy in our institution. All MR...

Full description

Bibliographic Details
Published in:Skeletal Radiology Vol. 49; no. 8; pp. 1207 - 1218
Main Authors: Fritz, Benjamin, Marbach, Giuseppe, Civardi, Francesco, Fucentese, Sandro F., Pfirrmann, Christian W.A.
Format: research Journal Article
Published: Springer Nature Aug2020
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=143819590&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 143819590
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        03642348
        O14
      jtl: Skeletal Radiology
      issn: 03642348
      maglogo: N
    pubinfo:
      dt: Aug2020
      vid: 49
      iid: 8
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        143819590
        143819590
        143972300
        NLM32170334
        143819590
        10.1007/s00256-020-03410-2
        NLM32170334
        143819590
      ppf: 1207
      ppct: 11
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Deep convolutional neural network-based detection of meniscus tears: comparison with radiologists and surgery as standard of reference.
      aug:
        au:
          Fritz, Benjamin
          Marbach, Giuseppe
          Civardi, Francesco
          Fucentese, Sandro F.
          Pfirrmann, Christian W.A.
        affil: Department of Radiology, Balgrist University Hospital, Forchstrasse 340, CH-8008, Zurich, Switzerland
      sug:
        subj:
          Male
          Middle Age
          Arthroscopy
          Female
          Adult
          Aged
          Adolescence
          Weights and Measures
          Clinical Competence
          Human
          Magnetic Resonance Imaging
          Retrospective Design
          Sensitivity and Specificity
          Comparative Studies
          Multicenter Studies
          Evaluation Research
          Validation Studies
          Middle Aged: 45-64 years
          Adult: 19-44 years
          Aged: 65+ years
          Adolescent: 13-18 years
          Male
          Female
      ab: Objective: To clinically validate a fully automated deep convolutional neural network (DCNN) for detection of surgically proven meniscus tears.Materials and Methods: One hundred consecutive patients were retrospectively included, who underwent knee MRI and knee arthroscopy in our institution. All MRI were evaluated for medial and lateral meniscus tears by two musculoskeletal radiologists independently and by DCNN. Included patients were not part of the training set of the DCNN. Surgical reports served as the standard of reference. Statistics included sensitivity, specificity, accuracy, ROC curve analysis, and kappa statistics.Results: Fifty-seven percent (57/100) of patients had a tear of the medial and 24% (24/100) of the lateral meniscus, including 12% (12/100) with a tear of both menisci. For medial meniscus tear detection, sensitivity, specificity, and accuracy were for reader 1: 93%, 91%, and 92%, for reader 2: 96%, 86%, and 92%, and for the DCNN: 84%, 88%, and 86%. For lateral meniscus tear detection, sensitivity, specificity, and accuracy were for reader 1: 71%, 95%, and 89%, for reader 2: 67%, 99%, and 91%, and for the DCNN: 58%, 92%, and 84%. Sensitivity for medial meniscus tears was significantly different between reader 2 and the DCNN (p = 0.039), and no significant differences existed for all other comparisons (all p ≥ 0.092). The AUC-ROC of the DCNN was 0.882, 0.781, and 0.961 for detection of medial, lateral, and overall meniscus tear. Inter-reader agreement was very good for the medial (kappa = 0.876) and good for the lateral meniscus (kappa = 0.741).Conclusion: DCNN-based meniscus tear detection can be performed in a fully automated manner with a similar specificity but a lower sensitivity in comparison with musculoskeletal radiologists.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N