On the generalized inverse for MRI reconstruction
Authors:
- 10 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Recent studies have suggested that the boundary between data-driven deep-learning non-Cartesian magnetic resonance imaging (MRI) reconstruction methods and conventional optimization-based, iterative reconstruction methods is becoming blurred. For instance, the unrolled iterative reconstruction method can be regarded as a trainable neural network. Another example is that the Moore-Penrose pseudoinverse plays a central role in finding the predefined solution to many imaging processes. However, the application of pseudoinverse in MRI reconstruction was obstructed in clinical imaging, mostly due to the excessive storage required for singular vectors. Since the spatial encoding of MRI is fully determined by the known k-space trajectory, the generalized inverse can be ”iteratively learning in a data-free fashion”, which leads to surprising but realizable properties. To compare our method with other conventional methods, numerical simulations were performed using in vivo MRI. The proposed method leads to nearly equivalent image quality with a much shorter run-time (only 0.68%) than the conjugate gradient (CG) method. We discuss the potential impact of the generalized inverse as a feasible reconstruction method for non-Cartesian MRI.Keywords
Funding Information
- Sin-Lau Hospital
This publication has 29 references indexed in Scilit:
- Iterative method for computing the Moore–Penrose inverse based on Penrose equationsJournal of Computational and Applied Mathematics, 2011
- Generalized approximate inverse preconditioners for least squares problemsJapan Journal of Industrial and Applied Mathematics, 2009
- Reconstruction of MR images from data acquired on a general nonregular grid by pseudoinverse calculationIEEE Transactions on Medical Imaging, 2000
- Approximate Inverse Preconditioners via Sparse-Sparse IterationsSIAM Journal on Scientific Computing, 1998
- Application of the Approximate Inverse to 3D X-Ray CT and Ultrasound Tomography1997
- A self-correcting matrix iteration for the Moore-Penrose generalized inverseLinear Algebra and its Applications, 1996
- Approximate inverse preconditionings for sparse linear systemsInternational Journal of Computer Mathematics, 1992
- On Iterative Computation of Generalized Inverses and Associated ProjectionsSIAM Journal on Numerical Analysis, 1966
- Generalized Inverse Computations Using the Gradient Projection MethodJournal of the ACM, 1964
- A generalized inverse for matricesMathematical Proceedings of the Cambridge Philosophical Society, 1955