OMERACT validation of a deep learning algorithm for automated absolute quantification of knee joint effusion versus manual semi-quantitative assessment.

Journal: Seminars in arthritis and rheumatism
Published Date:

Abstract

OBJECTIVE: To begin evaluating deep learning (DL)-automated quantification of knee joint effusion-synovitis via the OMERACT filter.

Authors

  • Banafshe Felfeliyan
    Biomedical Engineering, Schulich School of Engineering, University of Calgary, Canada.
  • Stephanie Wichuk
    Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Canada.
  • Abhilash R Hareendranathan
  • Robert G Lambert
    From the Institute for Radiology (K.K.B., L.C.A., K.G.A.H., T.D., S.M.N., B.H., J.L.V.) and Department of Gastroenterology, Infectious Diseases and Rheumatology (including Nutrition Medicine) (F.P., L.S., M.P., V.R.R., H.H., J.R., M.T., D.P.), Charité-Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; Berlin Institute of Health at Charité-Universitätsmedizin Berlin, Berlin, Germany (K.K.B., L.C.A., J.R.); Department of Diagnostic and Interventional Radiology, Faculty of Medicine, Technical University of Munich, Munich, Germany (M.R.M.); Department of Medicine, University of Alberta, Edmonton, Alberta, Canada (R.G.L., W.P.M.); Rheumazentrum Ruhrgebiet Herne, Ruhr University Bochum, Germany (X.B.); and Epidemiology Unit, German Rheumatism Research Centre, Berlin, Germany (D.P.).
  • Walter P Maksymowych
    Department of Medicine, University of Alberta, Canada.
  • Jacob Jaremko
    University of Alberta, Canada.