Network Accelerated Motion Estimation and Reduction (NAMER): Convolutional neural network guided retrospective motion correction using a separable motion model.

Journal: Magnetic resonance in medicine
Published Date: May 2, 2019

Abstract

PURPOSE: We introduce and validate a scalable retrospective motion correction technique for brain imaging that incorporates a machine learning component into a model-based motion minimization.

Authors

  • Melissa W Haskell
    A.A. Martinos Center for Biomedical Imaging, Department of Radiology, MGH, Charlestown, Massachusetts.
  • Stephen F Cauley
    A. A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, Massachusetts, USA.
  • Berkin Bilgic
    Department of Radiology, Harvard Medical School, Boston, MA, USA.
  • Julian Hossbach
    Siemens Healthcare, Erlangen, Germany.
  • Daniel N Splitthoff
    Siemens Healthcare, Erlangen, Germany.
  • Josef Pfeuffer
    Department of Diagnostic and Interventional Radiology, University Hospital Würzburg, Oberdürrbacher Strasse 6, 97080 Würzburg, Germany (J.F.H., S.V., C.M., L.M.P., T.A.B., H.K., A.M.W.); and Department of Application Development, Siemens Healthcare, Erlangen, Germany (T.B., J.P.).
  • Kawin Setsompop
    Department of Radiology, Harvard Medical School, Boston, MA, USA.
  • Lawrence L Wald
    Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, Massachusetts.

Keywords

External Resources

Popular Topics
Recent Journals