Computationally Efficient Implicit Training Strategy for Unrolled Networks (IMUNNE): A Preliminary Analysis Using Accelerated Real-Time Cardiac Cine MRI.

Journal: IEEE transactions on bio-medical engineering
Published Date: Jan 15, 2025

Abstract

OBJECTIVE: Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost.

Authors

  • Nikolay Iakovlev
  • Florian A Schiffers
  • Santiago L Tapia
  • Daming Shen
    Biomedical Engineering, McCormick School of Engineering and Applied Science, Northwestern University, Evanston, Illinois.
  • KyungPyo Hong
  • Michael Markl
    Department of Biomedical Engineering and Physics (J.T.P.) and Department of Radiology & Nuclear Medicine (P.v.O.), Academic Medical Center, Amsterdam University Medical Centers, Location AMC, Meibergdreef 9, 1105 AZ Amsterdam, the Netherlands; Department of Radiology (B.D.A., J.C.C., M.M.), Department of Medicine-Cardiology (R.O.B., L.C.), and Department of Biomedical Engineering (M.M.), Northwestern University, Chicago, Ill; and Department of Radiology & Bioengineering, Children's Hospital Colorado, University of Colorado Anschutz Medical Campus, Denver, Colo (A.J.B.).
  • Daniel C Lee
    Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois.
  • Aggelos K Katsaggelos
    Department of Electrical and Computer Engineering, McCormick School of Engineering and Applied Science, Northwestern University, Evanston, Illinois.
  • Daniel Kim
    Biomedical Engineering, McCormick School of Engineering and Applied Science, Northwestern University, Evanston, Illinois.

Keywords

External Resources

Popular Topics
Recent Journals