Impact of spectrum bias on deep learning-based stroke MRI analysis.

Journal: European journal of radiology
Published Date:

Abstract

PURPOSE: To evaluate spectrum bias in stroke MRI analysis by excluding cases with uncertain acute ischemic lesions (AIL) and examining patient, imaging, and lesion factors associated with these cases.

Authors

  • Christian Hedeager Krag
    From the Department of Radiology, Herlev and Gentofte Hospital, Borgmester Ib, Juuls vej 1 Herlev, Copenhagen 2730, Denmark (L.L.P., F.C.M., M.W.B., C.H.K., L.C.L., M.B.A.); Faculty of Health Sciences, University of Copenhagen, Copenhagen, Denmark (L.L.P., M.W.B., C.H.K., M.B., M.B.A.); Radiological Artificial Intelligence Testcenter, RAIT.dk, Herlev, Denmark (L.L.P., F.C.M., M.W.B., C.H.K., M.B., M.B.A.); Department of Radiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (M.W.B., M.B.); Department of Radiology, Aarhus University Hospital, Aarhus, Denmark (F.R.); and Department of Cardiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (O.W.N.).
  • Felix Christoph Müller
    Department of Radiology, Copenhagen University Hospital at Herlev and Gentofte, Denmark; Department of Clinical Physiology and Nuclear Medicine, Copenhagen University Hospital at Rigshospitalet, Denmark.
  • Karen Lind Gandrup
    University Hospital Copenhagen - Herlev and Gentofte, Department of Radiology, Denmark.
  • Louis Lind Plesner
    From the Department of Radiology, Herlev and Gentofte Hospital, Borgmester Ib, Juuls vej 1 Herlev, Copenhagen 2730, Denmark (L.L.P., F.C.M., M.W.B., C.H.K., L.C.L., M.B.A.); Faculty of Health Sciences, University of Copenhagen, Copenhagen, Denmark (L.L.P., M.W.B., C.H.K., M.B., M.B.A.); Radiological Artificial Intelligence Testcenter, RAIT.dk, Herlev, Denmark (L.L.P., F.C.M., M.W.B., C.H.K., M.B., M.B.A.); Department of Radiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (M.W.B., M.B.); Department of Radiology, Aarhus University Hospital, Aarhus, Denmark (F.R.); and Department of Cardiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (O.W.N.).
  • Malini Vendela Sagar
    Department of Clinical Medicine, University of Copenhagen, Denmark; University Hospital Copenhagen - Herlev and Gentofte, Department of Neurology, Denmark.
  • Michael Brun Andersen
    Aarhus University, Aarhus, Denmark; Herlev Gentofte Hospital, The Capital Region, Denmark.
  • Mads Nielsen
    Department of Computer Science, University of Copenhagen, Copenhagen Ø DK-2100, Denmark; Biomediq A/S, Copenhagen Ø DK-2100, Denmark.
  • Christina Kruuse
    Faculty of Health Sciences, University of Copenhagen, Copenhagen, Denmark; Department of Neurology, Herlev and Gentofte Hospital, Herlev, Denmark.
  • Mikael Boesen
    From the Department of Radiology, Herlev and Gentofte Hospital, Borgmester Ib Juuls vej 1, 2730 Herlev, Copenhagen, Denmark (L.L.P., F.C.M., L.C.L., M.B.A.); Faculty of Health Sciences, University of Copenhagen, Copenhagen, Denmark (L.L.P., O.W.N., M.B., M.B.A.); Radiological Artificial Intelligence Testcenter, RAIT.dk, Capital region of Denmark (L.L.P., F.C.M., J.D.N., M.B., M.B.A.); Department of Radiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (J.D.N., M.B.); Department of Radiology, Aarhus University Hospital, Aarhus, Denmark (F.R.); and Department of Cardiology, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark (O.W.N.).