Simultaneously optimizing sampling pattern for joint acceleration of multi‐contrast MRI using model‐based deep learning
Authors:
- 20 June 2022
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 49 (9) , 5964-5980
Abstract
Background: Acceleration of MR imaging (MRI) is a popular research area, and usage of deep learning for acceleration has become highly widespread in the MR community. Joint acceleration of multiple‐acquisition MRI was proven to be effective over a single‐acquisition approach. Also, optimization in the sampling pattern demonstrated its advantage over conventional undersampling pattern. However, optimizing the sampling patterns for joint acceleration of multiple‐acquisition MRI has not been investigated well.Purpose: To develop a model‐based deep learning scheme to optimize sampling patterns for a joint acceleration of multi‐contrast MRI.Methods: The proposed scheme combines sampling pattern optimization and multi‐contrast MRI reconstruction. It was extended from the physics‐guided method of the joint model–based deep learning (J‐MoDL) scheme to optimize the separate sampling pattern for each of multiple contrasts simultaneously for their joint reconstruction. Tests were performed with three contrasts of T2‐weighted, FLAIR, and T1‐weighted images. The proposed multi‐contrast method was compared to (i) single‐contrast method with sampling optimization (baseline J‐MoDL), (ii) multi‐contrast method without sampling optimization, and (iii) multi‐contrast method with single common sampling optimization for all contrasts. The optimized sampling patterns were analyzed for sampling location overlap across contrasts. The scheme was also tested in a data‐driven scenario, where the inversion between input and label was learned from the under‐sampled data directly and tested on knee datasets for generalization test.Results: The proposed scheme demonstrated a quantitative and qualitative advantage over the single‐contrast scheme with sampling pattern optimization and the multi‐contrast scheme without sampling pattern optimization. Optimizing the separate sampling pattern for each of the multi‐contrasts was superior to optimizing only one common sampling pattern for all contrasts. The proposed scheme showed less overlap in sampling locations than the single‐contrast scheme. The main hypothesis was also held in the data‐driven situation as well. The brain‐trained model worked well on the knee images, demonstrating its generalizability.Conclusion: Our study introduced an effective scheme that combines the sampling optimization and the multi‐contrast acceleration. The seamless combination resulted in superior performance over the other existing methods.Keywords
Funding Information
- National Research Foundation of Korea (NRF‐2020R1A4A1018714, NRF‐2020R1A2C2008949)
This publication has 31 references indexed in Scilit:
- Accelerating magnetic resonance imaging via deep learningIEEE International Symposium on Biomedical Imaging, 2016
- SimpleElastix: A User-Friendly, Multi-lingual Library for Medical Image Registration2016
- Fast multi-contrast MRI reconstructionMagnetic Resonance Imaging, 2014
- ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPAMagnetic Resonance in Medicine, 2013
- Fundamentals of balanced steady state free precession MRIJournal of Magnetic Resonance Imaging, 2013
- Multi‐contrast reconstruction with Bayesian compressed sensingMagnetic Resonance in Medicine, 2011
- Compressed sensingIEEE Transactions on Information Theory, 2006
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002
- Steady-State Free Precession in Nuclear Magnetic ResonancePhysical Review B, 1958
- Individual Comparisons by Ranking MethodsBiometrics Bulletin, 1945