A Self-Supervised Deep Learning Reconstruction for Shortening the Breathhold and Acquisition Window in Cardiac Magnetic Resonance Fingerprinting
Open Access
- 23 June 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Cardiovascular Medicine
- Vol. 9, 928546
Abstract
The aim of this study is to shorten the breathhold and diastolic acquisition window in cardiac magnetic resonance fingerprinting (MRF) for simultaneous T1, T2, and proton spin density (M0) mapping to improve scan efficiency and reduce motion artifacts. To this end, a novel reconstruction was developed that combines low-rank subspace modeling with a deep image prior, termed DIP-MRF. A system of neural networks is used to generate spatial basis images and quantitative tissue property maps, with training performed using only the undersampled k-space measurements from the current scan. This approach avoids difficulties with obtaining in vivo MRF training data, as training is performed de novo for each acquisition. Calculation of the forward model during training is accelerated by using GRAPPA operator gridding to shift spiral k-space data to Cartesian grid points, and by using a neural network to rapidly generate fingerprints in place of a Bloch equation simulation. DIP-MRF was evaluated in simulations and at 1.5 T in a standardized phantom, 18 healthy subjects, and 10 patients with suspected cardiomyopathy. In addition to conventional mapping, two cardiac MRF sequences were acquired, one with a 15-heartbeat(HB) breathhold and 254 ms acquisition window, and one with a 5HB breathhold and 150 ms acquisition window. In simulations, DIP-MRF yielded decreased nRMSE compared to dictionary matching and a sparse and locally low rank (SLLR-MRF) reconstruction. Strong correlation (R2 > 0.999) with T1 and T2 reference values was observed in the phantom using the 5HB/150 ms scan with DIP-MRF. DIP-MRF provided better suppression of noise and aliasing artifacts in vivo, especially for the 5HB/150 ms scan, and lower intersubject and intrasubject variability compared to dictionary matching and SLLR-MRF. Furthermore, it yielded a better agreement between myocardial T1 and T2 from 15HB/254 ms and 5HB/150 ms MRF scans, with a bias of −9 ms for T1 and 2 ms for T2. In summary, this study introduces an extension of the deep image prior framework for cardiac MRF tissue property mapping, which does not require pre-training with in vivo scans, and has the potential to reduce motion artifacts by enabling a shortened breathhold and acquisition window.Keywords
Funding Information
- Siemens Healthineers
This publication has 54 references indexed in Scilit:
- Identification and Assessment of Anderson-Fabry Disease by Cardiovascular Magnetic Resonance Noncontrast Myocardial T1 MappingCirculation: Cardiovascular Imaging, 2013
- Magnetic resonance fingerprintingNature, 2013
- Cardiovascular magnetic resonance by non contrast T1-mapping allows assessment of severity of injury in acute myocardial infarctionJournal of Cardiovascular Magnetic Resonance, 2012
- T2 quantification for improved detection of myocardial edemaJournal of Cardiovascular Magnetic Resonance, 2009
- Quantitative magnetization transfer imaging using balanced SSFPMagnetic Resonance in Medicine, 2008
- Non‐Cartesian data reconstruction using GRAPPA operator gridding (GROG)Magnetic Resonance in Medicine, 2007
- Modified Look‐Locker inversion recovery (MOLLI) for high‐resolution T1 mapping of the heartMagnetic Resonance in Medicine, 2004
- Nonuniform fast fourier transforms using min-max interpolationIEEE Transactions on Signal Processing, 2003
- Standardized Myocardial Segmentation and Nomenclature for Tomographic Imaging of the HeartCirculation, 2002
- STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENTThe Lancet, 1986