Deep Unrolling for Magnetic Resonance Fingerprinting

Dongdong Chen, Mike E. Davies, Mohammad Golbabaee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Magnetic Resonance Fingerprinting (MRF) has emerged as a promising quantitative MR imaging approach. Deep learning methods have been proposed for MRF and demonstrated improved performance over classical compressed sensing algorithms. However many of these end-to-end models are physics-free, while consistency of the predictions with respect to the physical forward model is crucial for reliably solving inverse problems. To address this, recently [1] proposed a proximal gradient descent framework that directly incorporates the forward acquisition and Bloch dynamic models within an unrolled learning mechanism. However, [1] only evaluated the unrolled model on synthetic data using Cartesian sampling trajectories. In this paper, as a complementary to [1], we investigate other choices of encoders to build the proximal neural network, and evaluate the deep unrolling algorithm on real accelerated MRF scans with non-Cartesian k-space sampling trajectories.
Original languageUndefined/Unknown
Title of host publication2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)
PublisherIEEE Xplore
ISBN (Electronic)978-1-6654-2923-8
Publication statusE-pub ahead of print - 26 Apr 2022
EventIEEE 19th International Symposium on Biomedical Imaging (ISBI) 2022 -
Duration: 28 Mar 202231 Mar 2022


ConferenceIEEE 19th International Symposium on Biomedical Imaging (ISBI) 2022
Abbreviated titleISBI

Keywords / Materials (for Non-textual outputs)

  • Deep unrolling
  • compressed sensing
  • magnetic resonance fingerprinting
  • quantitative MRI

Cite this